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

    Neuronpedia

    INDEX
    Explanations

    items or categories related to published works and distributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icl
    -0.16
    cke
    -0.15
    à¹Īำ
    -0.15
    vx
    -0.14
    otten
    -0.14
    amil
    -0.14
    .jsoup
    -0.14
    bia
    -0.13
    auer
    -0.13
    ivec
    -0.13
    POSITIVE LOGITS
     subrange
    0.15
     fisse
    0.15
    RI
    0.14
    afs
    0.14
     tier
    0.14
     Mount
    0.14
    PARATOR
    0.13
    olean
    0.13
    ybrid
    0.13
    loat
    0.13
    Act Density 0.040%

    No Known Activations