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

    Neuronpedia

    INDEX
    Explanations

    comparative language regarding quantities and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mastur
    -0.17
    ivol
    -0.16
    atro
    -0.15
    oningen
    -0.14
    .Buffer
    -0.14
    ql
    -0.14
    oleans
    -0.13
     pornografia
    -0.13
    jie
    -0.13
    iture
    -0.13
    POSITIVE LOGITS
    995
    0.22
     Incorporated
    0.18
    rug
    0.15
    urma
    0.15
     Zak
    0.15
    391
    0.15
    çݲ
    0.14
     jadx
    0.14
    OperationException
    0.14
    &action
    0.14
    Act Density 0.233%

    No Known Activations