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

    Neuronpedia

    INDEX
    Explanations

    phrases related to lending or providing support

    oai_token-act-pair · gpt-3.5-turbo

    verbs indicating contribution or support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alde
    -0.72
    anwhile
    -0.68
    anamo
    -0.64
    oppable
    -0.63
     Marathon
    -0.62
    gap
    -0.62
    Org
    -0.61
    å°Ĩ
    -0.61
    swick
    -0.61
     Malays
    -0.60
    POSITIVE LOGITS
     lent
    1.01
     lending
    0.96
     cred
    0.95
     lend
    0.95
    shire
    0.84
    owship
    0.80
    stocks
    0.78
    ament
    0.77
    icular
    0.73
    rils
    0.72
    Act Density 0.018%

    No Known Activations