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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing each individual item or person within a group

    oai_token-act-pair · gpt-3.5-turbo

    references to the phrase "every single" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orthy
    -0.87
    eln
    -0.79
    ello
    -0.77
    aline
    -0.76
    ctr
    -0.74
    anwhile
    -0.70
    arty
    -0.69
    olas
    -0.68
    ÃĥÃĤ
    -0.68
    HCR
    -0.68
    POSITIVE LOGITS
    THING
    1.23
     goddamn
    0.98
     imaginable
    0.96
    WHERE
    0.94
     conceivable
    0.89
     godd
    0.88
     dollar
    0.81
     penny
    0.81
     person
    0.80
     facet
    0.80
    Act Density 0.020%

    No Known Activations