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

    Neuronpedia

    INDEX
    Explanations

    verbs that imply a strong necessity or action

    oai_token-act-pair · gpt-3.5-turbo

    affirmations or strong statements of capability and necessity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Nile
    -0.74
     optionally
    -0.67
     admittedly
    -0.63
    anwhile
    -0.63
    vious
    -0.62
     appropriately
    -0.61
     Leone
    -0.60
    NYSE
    -0.60
     curiously
    -0.59
     alternatively
    -0.58
    POSITIVE LOGITS
    Buff
    0.80
    ĨĴ
    0.71
     Hoff
    0.69
    illon
    0.68
    hin
    0.68
    icable
    0.68
    rencies
    0.67
    ional
    0.66
    hing
    0.66
    ppa
    0.64
    Act Density 0.217%

    No Known Activations