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

    Neuronpedia

    INDEX
    Explanations

    Words related to conformity and consent

    oai_token-act-pair · gpt-3.5-turbo

    words related to forms and actions of agreement or conformity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atur
    -0.65
    anas
    -0.64
    brand
    -0.63
    wagen
    -0.62
    par
    -0.62
    apon
    -0.61
    por
    -0.61
    apped
    -0.60
    vell
    -0.60
    izons
    -0.59
    POSITIVE LOGITS
    LY
    0.91
    ly
    0.88
    lihood
    0.80
    nesses
    0.74
    urally
    0.72
    TY
    0.71
    soever
    0.65
    ysis
    0.64
    xual
    0.64
    ially
    0.62
    Act Density 0.421%

    No Known Activations