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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating collective responsibility or action

    oai_token-act-pair · gpt-3.5-turbo

    collective phrases emphasizing communal experiences and needs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    luster
    -0.63
     arresting
    -0.59
    limit
    -0.59
     exclusion
    -0.58
    ahime
    -0.58
    FN
    -0.57
    LR
    -0.55
    none
    -0.54
     promotion
    -0.54
    flation
    -0.54
    POSITIVE LOGITS
     alike
    1.03
    ocating
    0.99
     agree
    0.89
     know
    0.88
    uding
    0.84
     kinds
    0.83
     owe
    0.80
     remember
    0.77
    know
    0.76
     knew
    0.76
    Act Density 0.034%

    No Known Activations