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

    Neuronpedia

    INDEX
    Explanations

    phrases revolving around statements or assertions

    oai_token-act-pair · gpt-3.5-turbo

    affirmative or confirmatory statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    İĭ
    -0.83
    flows
    -0.82
    ĻĤ
    -0.77
    gall
    -0.73
    ģ«
    -0.73
    ounded
    -0.68
    lines
    -0.68
    ethyst
    -0.67
    lain
    -0.66
    rities
    -0.66
    POSITIVE LOGITS
     sir
    0.85
     yes
    0.74
     Woo
    0.73
    terday
    0.71
     thank
    0.67
     ol
    0.66
    aah
    0.64
     Anders
    0.63
     Carolyn
    0.61
     Mistress
    0.61
    Act Density 0.066%

    No Known Activations