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

    Neuronpedia

    INDEX
    Explanations

    phrases related to decisions or intentions expressed in the future

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "would."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cius
    -0.78
    DAQ
    -0.72
     sqor
    -0.63
    efeated
    -0.61
    RAM
    -0.60
    ception
    -0.59
    ancer
    -0.58
    chemy
    -0.58
    Lear
    -0.57
     Parables
    -0.57
    POSITIVE LOGITS
    ĸļ
    0.90
     never
    0.89
     gladly
    0.84
     be
    0.83
     eventually
    0.79
     soon
    0.77
     reopen
    0.74
     donate
    0.74
     leave
    0.74
    aido
    0.73
    Act Density 0.164%

    No Known Activations