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

    Neuronpedia

    INDEX
    Explanations

    phrases questioning or comparing actions or choices

    oai_token-act-pair · gpt-3.5-turbo

    be verbs that question the nature or morality of actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esa
    -0.69
    places
    -0.64
    aneers
    -0.64
     Working
    -0.63
     Dreams
    -0.61
     Dragonbound
    -0.61
    FTWARE
    -0.59
     Position
    -0.59
    cko
    -0.58
    irds
    -0.57
    POSITIVE LOGITS
    omorphic
    0.83
    Ļ½
    0.80
    hap
    0.78
    nt
    0.73
    gur
    0.72
    berra
    0.71
    olated
    0.68
     anybody
    0.68
    earch
    0.68
    senal
    0.65
    Act Density 0.130%

    No Known Activations