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

    Neuronpedia

    INDEX
    Explanations

    references to specific individuals or entities, particularly names with the prefix "Go" or "Gö"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sov
    -0.16
    upo
    -0.16
    ced
    -0.15
    enti
    -0.15
    enser
    -0.15
    antly
    -0.14
    omm
    -0.14
    vice
    -0.14
    nton
    -0.14
    erer
    -0.14
    POSITIVE LOGITS
    VERN
    0.25
    /fwlink
    0.22
    ÅĽcie
    0.18
    ebb
    0.17
    ethe
    0.17
    ekli
    0.17
    SSIP
    0.16
    mez
    0.15
    zilla
    0.15
    ogle
    0.15
    Act Density 0.029%

    No Known Activations