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

    Neuronpedia

    INDEX
    Explanations

    verbs that express desire or wish

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing hopes and aspirations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     [-
    -0.63
     liable
    -0.63
    note
    -0.63
    acid
    -0.62
     Matter
    -0.60
     wastes
    -0.59
     brackets
    -0.58
     acid
    -0.57
     clipboard
    -0.57
     prone
    -0.56
    POSITIVE LOGITS
    llers
    0.79
     someday
    0.76
     revival
    0.70
     emulate
    0.69
     fulfil
    0.68
     bargain
    0.66
    eele
    0.65
     succeed
    0.64
    ãĤ´ãĥ³
    0.64
    ffer
    0.64
    Act Density 0.053%

    No Known Activations