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

    Neuronpedia

    INDEX
    Explanations

    references to quantities or numerical relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    \{\\
    -0.59
    uxxxx
    -0.58
     &___
    -0.56
     ProtoMessage
    -0.55
    ⤒
    -0.55
     كومونز
    -0.54
    Équipe
    -0.54
     betweenstory
    -0.53
     iprot
    -0.53
     typelib
    -0.52
    POSITIVE LOGITS
    Others
    0.57
     Others
    0.57
     mainly
    0.56
     mostly
    0.52
    InlineData
    0.52
     formerly
    0.52
    mainly
    0.52
     primarily
    0.50
     others
    0.47
    formerly
    0.47
    Act Density 0.420%

    No Known Activations