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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating actions, intentions, or plans involving future activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pmat
    -0.16
    raz
    -0.14
     kvinna
    -0.13
    oksen
    -0.13
    _requires
    -0.13
    æ³³
    -0.13
    gars
    -0.13
    assis
    -0.12
    emen
    -0.12
    ropa
    -0.12
    POSITIVE LOGITS
    758
    0.16
    keh
    0.16
     ifndef
    0.16
     lit
    0.16
    ea
    0.15
     Hut
    0.14
     doing
    0.14
    552
    0.14
     Cue
    0.13
     Kostenlose
    0.13
    Act Density 0.420%

    No Known Activations