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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating quantity or numerical significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    󠁿
    -0.50
     trebui
    -0.48
    ︎
    -0.47
     NoSuch
    -0.47
    hawar
    -0.47
    prav
    -0.46
    StandardCharsets
    -0.41
     PV
    -0.41
    ओं
    -0.41
    HasIndex
    -0.41
    POSITIVE LOGITS
     AMONG
    1.09
     Amongst
    0.99
    among
    0.98
     Among
    0.95
     among
    0.94
    śród
    0.94
    Among
    0.93
     amongst
    0.88
    Parmi
    0.84
     parmi
    0.83
    Act Density 0.039%

    No Known Activations