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

    Neuronpedia

    INDEX
    Explanations

    texts that discuss existential or philosophical topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     iſt
    -0.76
     Majefty
    -0.73
    extAlignment
    -0.71
     Jefus
    -0.69
     Saltar
    -0.66
     faſt
    -0.65
    ]--;
    -0.65
     purpoſe
    -0.65
    ſelf
    -0.64
     Anſ
    -0.64
    POSITIVE LOGITS
     <=",
    0.69
     Roskov
    0.61
     ModelExpression
    0.58
    ثيق
    0.57
    thâu
    0.51
    WithIOException
    0.51
     INSEE
    0.50
     {
    0.48
    وردار
    0.48
    stantial
    0.46
    Act Density 0.919%

    No Known Activations