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

    Neuronpedia

    INDEX
    Explanations

    sentences discussing hypothetical situations or future actions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of future possibilities and hypothetical scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Fine
    -0.63
    artisan
    -0.62
     Tick
    -0.62
    ancer
    -0.61
     LTD
    -0.59
     Shooting
    -0.58
     Perfect
    -0.57
     Fancy
    -0.57
    Arcade
    -0.56
     Provided
    -0.56
    POSITIVE LOGITS
     be
    0.94
     entail
    0.84
     avail
    0.84
     tolerate
    0.80
     feas
    0.78
     achieve
    0.77
    »Ĵ
    0.77
     survive
    0.77
     arrive
    0.76
     accomplish
    0.76
    Act Density 0.155%

    No Known Activations