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

    Neuronpedia

    INDEX
    Explanations

    verb phrases related to discussing or explaining actions

    oai_token-act-pair · gpt-3.5-turbo

    verbs indicating actions related to decision-making processes or legal proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nown
    -0.91
    ersen
    -0.76
    oglu
    -0.70
    nen
    -0.66
    Whit
    -0.65
    oÄŁ
    -0.63
     bluff
    -0.63
    usra
    -0.62
    ère
    -0.62
    izons
    -0.61
    POSITIVE LOGITS
     FORM
    0.74
     Souls
    0.70
     materials
    0.67
     INTO
    0.65
     mankind
    0.62
     souls
    0.61
     mode
    0.61
     spheres
    0.61
     form
    0.60
     regard
    0.60
    Act Density 0.157%

    No Known Activations