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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating size or magnitude

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oot
    -0.17
     Poss
    -0.16
    à¥įह
    -0.15
    itol
    -0.14
     Wonder
    -0.14
    soever
    -0.14
    mc
    -0.14
    pliers
    -0.14
    mh
    -0.14
     storm
    -0.13
    POSITIVE LOGITS
    pike
    0.18
    ëļ
    0.16
    leine
    0.16
    strup
    0.15
    precated
    0.15
    _TUN
    0.14
    ogy
    0.14
    (chan
    0.14
    çĽijåIJ¬é¡µéĿ¢
    0.13
    apiro
    0.13
    Act Density 0.030%

    No Known Activations