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

    Neuronpedia

    INDEX
    Explanations

    hyphenated words indicating intensity or completeness

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to "full-time" concepts or positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ń·
    -0.80
     Tycoon
    -0.74
     Miko
    -0.70
     Pok
    -0.68
     charms
    -0.67
     Zar
    -0.65
     Richards
    -0.64
     Cah
    -0.64
     Hazard
    -0.63
     Phi
    -0.63
    POSITIVE LOGITS
    fledged
    1.46
    blown
    1.22
    sized
    1.17
    bodied
    1.15
    scale
    1.09
    employment
    1.04
    contact
    1.02
    strength
    1.01
    length
    1.01
    priced
    1.01
    Act Density 0.021%

    No Known Activations