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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing a broad range of experiences, options, and possibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    linky
    -0.17
    pend
    -0.16
    atoi
    -0.15
    rage
    -0.15
    itsu
    -0.15
    mite
    -0.15
    许
    -0.14
    illin
    -0.14
    kus
    -0.14
    udging
    -0.14
    POSITIVE LOGITS
     etc
    0.18
     Ster
    0.15
    nge
    0.15
    bett
    0.15
     Bench
    0.15
    etc
    0.15
    oreach
    0.14
    CEPTION
    0.14
    _https
    0.14
     Mile
    0.14
    Act Density 0.071%

    No Known Activations