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

    Neuronpedia

    INDEX
    Explanations

    mathematical equalities or comparisons

    oai_token-act-pair · gpt-3.5-turbo

    words related to equality and comparison

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hower
    -0.67
     Tart
    -0.65
     rocked
    -0.61
    schild
    -0.58
     Unch
    -0.56
    culosis
    -0.55
     collaboration
    -0.55
     moot
    -0.55
     Raider
    -0.54
     constructive
    -0.54
    POSITIVE LOGITS
    ivil
    1.12
    itably
    1.08
    ilib
    1.02
    aling
    0.99
    iv
    0.97
    ilateral
    0.95
    aled
    0.94
    anim
    0.92
    alling
    0.91
    alled
    0.89
    Act Density 0.023%

    No Known Activations