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

    Neuronpedia

    INDEX
    Explanations

    phrases related to things being firmly or securely in place

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating strong convictions or assertions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pmwiki
    -0.86
     Emin
    -0.84
    externalActionCode
    -0.84
    olan
    -0.77
    vernment
    -0.75
     Journals
    -0.72
    ammy
    -0.72
    NetMessage
    -0.71
    sites
    -0.70
    ebin
    -0.69
    POSITIVE LOGITS
     firmly
    1.11
     cement
    0.86
     conclud
    0.83
     rooted
    0.83
     adherent
    0.80
     ens
    0.80
    lishes
    0.79
     entrenched
    0.78
     positioned
    0.78
     planted
    0.78
    Act Density 0.006%

    No Known Activations