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

    Neuronpedia

    INDEX
    Explanations

    phrases related to compliance or agreement

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "go along."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inction
    -0.65
    ĻĤ
    -0.64
    ilies
    -0.62
    TY
    -0.60
     pitted
    -0.59
    ns
    -0.58
    ptive
    -0.57
    NAS
    -0.57
     wipe
    -0.57
    Rated
    -0.56
    POSITIVE LOGITS
    wagon
    0.82
    erous
    0.73
     Vest
    0.70
    agons
    0.67
    *=-
    0.66
    along
    0.65
     wagon
    0.65
    orest
    0.63
    estern
    0.63
    agon
    0.62
    Act Density 0.016%

    No Known Activations