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

    Neuronpedia

    INDEX
    Explanations

    sequences of tabs or whitespace

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SourceChecksum
    -1.24
    IsMutable
    -1.03
    complexType
    -0.97
     pleaſure
    -0.95
     useAppContext
    -0.94
     themſelves
    -0.94
     myſelf
    -0.94
     itſelf
    -0.94
     Monfieur
    -0.93
    AccessorTable
    -0.93
    POSITIVE LOGITS
     a
    0.52
     I
    0.50
    <eos>
    0.49
     T
    0.48
     X
    0.46
     well
    0.45
     the
    0.44
     same
    0.43
     and
    0.42
     for
    0.42
    Act Density 0.103%

    No Known Activations