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

    Neuronpedia

    INDEX
    Explanations

    phrases related to responsible actions and rational conduct

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

    actions and their circumstances

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    contentLoaded
    -0.53
    InputBorder
    -0.49
     nahilalakip
    -0.45
    providedIn
    -0.43
    atigable
    -0.43
    delwed
    -0.43
    opend
    -0.42
    colgroup
    -0.42
     cruc
    -0.41
     Teb
    -0.41
    POSITIVE LOGITS
    Acting
    0.85
     acted
    0.84
     actúa
    0.81
     Acting
    0.81
     acting
    0.80
     agir
    0.79
     acción
    0.79
     action
    0.76
     actuación
    0.75
     bertindak
    0.73
    Act Density 0.051%

    No Known Activations