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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "prior" or prior experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    es
    -0.79
    e
    -0.77
     Cassel
    -0.73
     Wissenschaften
    -0.73
    ecological
    -0.69
    Brunswick
    -0.68
     Seitz
    -0.67
    führ
    -0.66
    뀐
    -0.66
     Beetle
    -0.66
    POSITIVE LOGITS
     Pryor
    0.94
    AndEndTag
    0.91
    PRIOR
    0.89
     PRIOR
    0.87
    prior
    0.81
     priors
    0.80
     SAGE
    0.79
    Raptor
    0.78
     Prior
    0.77
     prior
    0.77
    Act Density 0.096%

    No Known Activations