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

    Neuronpedia

    INDEX
    Explanations

    instances of time-related phrases indicating sequential actions or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erview
    -0.15
    iling
    -0.15
    >NN
    -0.14
    amation
    -0.14
    elve
    -0.14
     nues
    -0.14
    寿
    -0.13
    ugal
    -0.13
    اة
    -0.13
    abbit
    -0.13
    POSITIVE LOGITS
    ãĥ«ãĥķ
    0.14
    essa
    0.14
    upp
    0.14
    ìĭł
    0.14
     READY
    0.14
    bler
    0.14
     zemÃŃ
    0.14
    วรรà¸ĵ
    0.14
    assa
    0.13
    ิà¸ĩห
    0.13
    Act Density 0.124%

    No Known Activations