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

    Neuronpedia

    INDEX
    Explanations

    expressions related to anticipation or expectation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pro
    -0.15
    Carthy
    -0.15
    ,
    -0.15
    eward
    -0.14
     \
    -0.14
    ateau
    -0.14
    ino
    -0.14
    erval
    -0.14
    etta
    -0.14
    enheim
    -0.14
    POSITIVE LOGITS
    resco
    0.17
    ingly
    0.16
    roc
    0.16
    woord
    0.15
    ãĥ¼ãĥĭ
    0.15
    .ExecuteScalar
    0.15
    edList
    0.14
    ãģ£ãģ¨
    0.14
     backpage
    0.14
    oga
    0.14
    Act Density 0.033%

    No Known Activations