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

    Neuronpedia

    INDEX
    Explanations

    mentions of buttons

    oai_token-act-pair · gpt-3.5-turbo

    references to physical buttons on devices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    INAL
    -0.78
    athan
    -0.77
    yss
    -0.77
    EG
    -0.76
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.76
    ×
    -0.71
    EEE
    -0.71
    sted
    -0.69
    ENCE
    -0.69
    noon
    -0.68
    POSITIVE LOGITS
     buttons
    1.14
    heet
    1.07
    mith
    1.04
    uits
    1.03
    paces
    0.97
    pace
    0.96
    pins
    0.95
    uggest
    0.95
    hooting
    0.94
    peed
    0.93
    Act Density 0.022%

    No Known Activations