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

    Neuronpedia

    INDEX
    Explanations

    references to authors and their publications

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     lenker
    -0.70
     Tartar
    -0.63
    binaan
    -0.62
     muualla
    -0.61
     NSCoder
    -0.61
     cauſe
    -0.59
     Diſ
    -0.59
     pleaſure
    -0.59
    ſelf
    -0.59
     Anſ
    -0.59
    POSITIVE LOGITS
    setVerticalGroup
    0.59
    apiClient
    0.57
    )))),
    0.56
     tartalomajánló
    0.55
    gisi
    0.55
    ']")
    0.52
    oneofs
    0.51
    olume
    0.50
    ResumeLayout
    0.49
    ())),
    0.48
    Act Density 0.168%

    No Known Activations