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

    Neuronpedia

    INDEX
    Explanations

    mentions of the word "kill" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    opause
    -0.16
    unc
    -0.15
    ew
    -0.14
     Mush
    -0.14
    -up
    -0.14
    Posts
    -0.14
    zzo
    -0.14
    ole
    -0.13
     ent
    -0.13
    eto
    -0.13
    POSITIVE LOGITS
    switch
    0.21
    roys
    0.18
    AdapterFactory
    0.18
     switches
    0.18
    ough
    0.17
    Switch
    0.17
    _dependency
    0.17
    ä»·
    0.17
    _SWITCH
    0.16
    ingly
    0.16
    Act Density 0.009%

    No Known Activations