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

    Neuronpedia

    INDEX
    Explanations

    expressions of dedication or commitment

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing commitment to specific causes or values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adish
    -0.88
    ENA
    -0.68
    AMA
    -0.64
     Cheong
    -0.62
    oa
    -0.60
    ramid
    -0.60
    oshop
    -0.59
    ahi
    -0.59
    uman
    -0.59
    ena
    -0.59
    POSITIVE LOGITS
    onite
    0.78
    unic
    0.78
    expr
    0.78
     adherent
    0.72
     targ
    0.71
    strong
    0.71
    duty
    0.70
    LY
    0.69
     enough
    0.69
    lly
    0.69
    Act Density 0.059%

    No Known Activations