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

    Neuronpedia

    INDEX
    Explanations

    words related to polling and survey results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    he
    -0.17
     Noir
    -0.15
     Goldberg
    -0.15
    ATS
    -0.14
    ccount
    -0.14
    721
    -0.14
    OS
    -0.14
    abox
    -0.14
    676
    -0.14
    ikat
    -0.14
    POSITIVE LOGITS
    ombo
    0.15
    zilla
    0.15
    RequiredMixin
    0.15
    acemark
    0.15
     limburg
    0.15
    StateManager
    0.15
    _ASSUME
    0.14
    oreach
    0.14
    orca
    0.14
    оÑĩнÑĭй
    0.14
    Act Density 0.007%

    No Known Activations