Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to appreciation, intention, and positive qualities of individuals or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Adjectives describing something good or correct

    np_acts-logits-general · gemini-2.0-flash

    admirable ideals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UnusedPrivate
    -0.66
    êté
    -0.52
     segredo
    -0.50
    racite
    -0.49
    ="#"><
    -0.49
    ingtones
    -0.49
    netbeans
    -0.48
    ANI
    -0.48
     préf
    -0.47
     optima
    -0.47
    POSITIVE LOGITS
     otherwise
    0.68
     immerhin
    0.67
     attempted
    0.64
     attempting
    0.63
     overall
    0.62
     intentions
    0.62
     nominally
    0.61
     ostensibly
    0.60
     attempts
    0.60
     ellers
    0.60
    Act Density 0.288%

    No Known Activations