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

    Neuronpedia

    INDEX
    Explanations

    expressions of agreement or acknowledgment

    oai_token-act-pair · gpt-3.5-turbo

    affirmative responses or expressions of agreement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Asylum
    -0.72
     Formation
    -0.62
    cephal
    -0.57
     Guinness
    -0.54
     Hug
    -0.54
    ULT
    -0.54
    Kick
    -0.52
     SHARES
    -0.51
     Thr
    -0.51
     Brist
    -0.51
    POSITIVE LOGITS
    soDeliveryDate
    0.81
    yang
    0.79
    endif
    0.75
    morrow
    0.67
    ooky
    0.67
    cember
    0.66
    rail
    0.66
    TextColor
    0.65
    ods
    0.64
    etheless
    0.63
    Act Density 0.591%

    No Known Activations