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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating alternatives or options

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ropolis
    -0.18
    mens
    -0.16
    STA
    -0.15
    .TypeOf
    -0.15
    cov
    -0.15
    Ư
    -0.15
    _parms
    -0.15
    actionDate
    -0.14
    jeme
    -0.14
    illet
    -0.14
    POSITIVE LOGITS
    hev
    0.17
     secular
    0.17
    avor
    0.16
    inski
    0.16
     be
    0.15
    ors
    0.15
     Cue
    0.15
    heet
    0.15
    ibilit
    0.14
    oftware
    0.14
    Act Density 0.022%

    No Known Activations