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

    Neuronpedia

    INDEX
    Explanations

    expressions related to favorites and chances of winning in competitive contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    anticipated outcomes and favorites

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     دیکھیے
    -0.49
     JADX
    -0.46
    ftance
    -0.44
     cref
    -0.44
     Mika
    -0.42
    Opere
    -0.41
    JET
    -0.41
    DataBean
    -0.41
    example
    -0.40
    gapa
    -0.40
    POSITIVE LOGITS
     expecting
    0.39
     expectations
    0.39
     expected
    0.39
     صوتيه
    0.39
    UnusedPrivate
    0.39
     chances
    0.39
     تكبرها
    0.39
     hyped
    0.38
     matchups
    0.38
     underdog
    0.38
    Act Density 0.156%

    No Known Activations