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

    Neuronpedia

    INDEX
    Explanations

    phrases related to planning and intentions

    oai_token-act-pair · gpt-3.5-turbo

    references to creative projects and planning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hest
    -0.76
    bound
    -0.65
    arest
    -0.65
     cannot
    -0.65
    ety
    -0.64
    imum
    -0.63
     helpless
    -0.63
    htaking
    -0.63
     unquestion
    -0.62
     evidently
    -0.61
    POSITIVE LOGITS
     someday
    1.18
     somew
    1.09
     another
    0.94
     sequels
    0.91
     MORE
    0.88
     bigger
    0.87
     something
    0.86
     more
    0.86
     some
    0.85
     commissions
    0.81
    Act Density 0.509%

    No Known Activations