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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating lack or scarcity

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a lack of quantity or variety

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idon
    -0.90
    yne
    -0.84
    ysc
    -0.81
    adia
    -0.81
    İĭ
    -0.77
    otom
    -0.76
    eneg
    -0.76
    initely
    -0.74
    swick
    -0.73
    oking
    -0.72
    POSITIVE LOGITS
     else
    0.97
     avail
    0.94
     ado
    0.87
     consolation
    0.82
     fuss
    0.75
     appreciated
    0.72
     resembles
    0.72
     appreci
    0.72
     resembling
    0.71
     luck
    0.69
    Act Density 0.030%

    No Known Activations