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

    Neuronpedia

    INDEX
    Explanations

    references to diplomatic dialogue and security measures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    toolbox
    -0.15
    haven
    -0.15
    plen
    -0.14
     Haskell
    -0.14
    xfff
    -0.14
    ooke
    -0.14
    imdi
    -0.14
     vielleicht
    -0.14
    sep
    -0.13
     platinum
    -0.13
    POSITIVE LOGITS
    ohan
    0.16
    бÑĭ
    0.15
    itzer
    0.15
    flare
    0.15
    ient
    0.15
    IENT
    0.15
    usan
    0.14
    onto
    0.14
    ayer
    0.14
     Northeast
    0.14
    Act Density 0.001%

    No Known Activations