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

    Neuronpedia

    INDEX
    Explanations

    variations and versions of concepts or items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ayer
    -0.20
    AYER
    -0.17
    ucc
    -0.16
    thag
    -0.16
    uhn
    -0.16
    hack
    -0.16
    STRU
    -0.15
    ÑĤÑĥÑĢа
    -0.15
    ilia
    -0.15
    obe
    -0.14
    POSITIVE LOGITS
    enie
    0.16
    IAM
    0.15
    è´µ
    0.14
     expression
    0.14
    inerary
    0.14
    .pen
    0.14
    /ne
    0.14
    unuz
    0.14
     ne
    0.13
     sos
    0.13
    Act Density 0.121%

    No Known Activations