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

    Neuronpedia

    INDEX
    Explanations

    questions and queries indicating skepticism or inquiry

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     why
    -0.60
    BagConstraints
    -0.60
     interessieren
    -0.56
     Truly
    -0.55
     Margo
    -0.54
     Gründe
    -0.53
     exactly
    -0.53
     araña
    -0.52
     proč
    -0.52
    Flynn
    -0.52
    POSITIVE LOGITS
    UserScript
    0.92
     שוליים
    0.74
    enumii
    0.73
    ^(@)
    0.73
     للمعارف
    0.73
    hoid
    0.72
    tanleria
    0.72
     $_"
    0.71
    WebElementEntity
    0.69
    <%@
    0.69
    Act Density 0.010%

    No Known Activations