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

    Neuronpedia

    INDEX
    Explanations

    commands or calls to action, often related to navigation or following links

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abr
    -0.18
    assen
    -0.17
    lasses
    -0.16
    elson
    -0.16
    ulse
    -0.15
    ray
    -0.14
    illo
    -0.14
    ковой
    -0.14
    ãĥªãĥ¼
    -0.14
    üç
    -0.14
    POSITIVE LOGITS
    thic
    0.25
    VERN
    0.23
    /fwlink
    0.22
    ÅĽcie
    0.20
    ings
    0.20
    SSIP
    0.18
    ekli
    0.18
    ÅĤÄħ
    0.17
    ertz
    0.17
    รษ
    0.16
    Act Density 0.048%

    No Known Activations