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

    Neuronpedia

    INDEX
    Explanations

    the presence of characters followed by punctuation indicating speech or thoughts

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks or connectors in complex sentence structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atars
    -0.75
    zel
    -0.74
    visor
    -0.71
     newcom
    -0.69
    asso
    -0.68
    amiliar
    -0.68
    ortment
    -0.66
    reet
    -0.65
    haul
    -0.64
    ilated
    -0.63
    POSITIVE LOGITS
     nor
    1.95
     anymore
    1.52
    yet
    1.27
    nor
    1.17
     Nor
    1.13
     whatsoever
    1.09
     unless
    0.97
     except
    0.95
    unless
    0.92
    Nor
    0.89
    Act Density 0.744%

    No Known Activations