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

    Neuronpedia

    INDEX
    Explanations

    structured academic references or citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     perm
    -0.16
     ("
    -0.16
     Dot
    -0.15
     (“
    -0.14
    mental
    -0.14
     disp
    -0.14
    lassian
    -0.14
    ourt
    -0.14
    Property
    -0.14
     dst
    -0.14
    POSITIVE LOGITS
    venta
    0.16
     Morse
    0.15
    -fetch
    0.15
     tesis
    0.15
    oses
    0.15
    bib
    0.14
     xlink
    0.14
    avras
    0.14
    annes
    0.14
    ruc
    0.14
    Act Density 0.006%

    No Known Activations