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

    Neuronpedia

    INDEX
    Explanations

    references to research findings and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ddelweddau
    -0.59
    曖昧さ回避
    -0.56
     err
    -0.51
     caoutchouc
    -0.48
    ніципа
    -0.47
    InputTagHelper
    -0.47
     perché
    -0.47
     esist
    -0.46
    DECREF
    -0.46
     approu
    -0.44
    POSITIVE LOGITS
     Findings
    0.72
     findings
    0.70
    Findings
    0.66
     insights
    0.62
    pyplot
    0.61
     Statistics
    0.60
     demografica
    0.59
    ViewFeatures
    0.59
    Statistics
    0.59
     Erkenntnisse
    0.59
    Act Density 0.852%

    No Known Activations