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

    Neuronpedia

    INDEX
    Explanations

    verbs in the passive voice

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate expectations or norms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tex
    -0.77
    roads
    -0.75
    sv
    -0.72
    lite
    -0.70
    lake
    -0.69
    mens
    -0.68
    collar
    -0.68
    lust
    -0.67
    pu
    -0.67
    east
    -0.65
    POSITIVE LOGITS
     disclaim
    0.80
    escription
    0.73
     explan
    0.71
     inconsist
    0.69
    entious
    0.67
     conflic
    0.67
    DonaldTrump
    0.67
    ELF
    0.67
    pport
    0.65
    ¾
    0.64
    Act Density 0.027%

    No Known Activations