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

    Neuronpedia

    INDEX
    Explanations

    references to studies or research investigations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    s
    -0.82
     skar
    -0.70
     -*-
    -0.65
    LikeLike
    -0.65
     Dickerson
    -0.63
    langle
    -0.62
    (
    -0.60
    TRUNC
    -0.60
     sinusoidal
    -0.60
    Neill
    -0.60
    POSITIVE LOGITS
     study
    2.05
     studies
    1.98
    STUDY
    1.90
    study
    1.90
     Study
    1.87
    Study
    1.77
    studies
    1.74
     STUDY
    1.73
     Studies
    1.62
     studying
    1.57
    Act Density 0.096%

    No Known Activations