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

    Neuronpedia

    INDEX
    Explanations

    verbs indicating potential future events

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing inevitability or potential future events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rador
    -0.79
    ilts
    -0.73
    stra
    -0.72
    edged
    -0.72
    cius
    -0.71
    mens
    -0.68
    otto
    -0.65
    oyal
    -0.65
    ondo
    -0.65
    rete
    -0.64
    POSITIVE LOGITS
    uate
    0.93
    NetMessage
    0.73
     happen
    0.71
    uates
    0.71
     anywhere
    0.70
     unfold
    0.70
    rences
    0.69
    uating
    0.68
     anytime
    0.67
     happening
    0.67
    Act Density 0.041%

    No Known Activations