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

    Neuronpedia

    INDEX
    Explanations

    conditional statements and expressions of uncertainty or speculation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÄĽk
    -0.15
     occasionally
    -0.15
    ometimes
    -0.15
    ureka
    -0.15
    acias
    -0.14
    óng
    -0.14
     opak
    -0.14
    amespace
    -0.14
    ç«Ł
    -0.14
    /wiki
    -0.14
    POSITIVE LOGITS
     fingers
    0.28
     given
    0.27
     Odds
    0.26
     odds
    0.26
     will
    0.25
     whether
    0.24
     based
    0.23
    given
    0.23
     anything
    0.23
     expect
    0.23
    Act Density 0.310%

    No Known Activations