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

    Neuronpedia

    INDEX
    Explanations

    phrases related to affiliation or association with a particular group or organization

    oai_token-act-pair · gpt-3.5-turbo

    terms related to affiliation or association with organizations or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pter
    -0.79
    =-=-=-=-=-=-=-=-
    -0.71
    aqu
    -0.69
    thur
    -0.68
    Prince
    -0.67
    pp
    -0.67
    bra
    -0.67
    MQ
    -0.65
     Leopard
    -0.64
    Herm
    -0.63
    POSITIVE LOGITS
     affili
    1.24
     affiliated
    1.21
    iliated
    1.12
     affiliation
    0.99
    hips
    0.93
    iliate
    0.85
     affiliate
    0.85
    lia
    0.85
     credential
    0.81
     affiliates
    0.79
    Act Density 0.012%

    No Known Activations