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

    Neuronpedia

    INDEX
    Explanations

    names or mentions of specific individuals

    oai_token-act-pair · gpt-3.5-turbo

    names related to a specific individual, likely in the context of activism or a company

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    é¾įå¥ij士
    -0.82
    ©¶æ
    -0.81
     Archdemon
    -0.76
    ccording
    -0.72
    å§
    -0.71
     indebted
    -0.68
    xious
    -0.67
     Flavoring
    -0.66
     magnification
    -0.66
    glers
    -0.65
    POSITIVE LOGITS
    enhagen
    0.86
    tein
    0.83
    illions
    0.82
    anamo
    0.82
    hemy
    0.81
    steen
    0.81
    ieri
    0.80
    coni
    0.80
    inen
    0.78
    nih
    0.78
    Act Density 0.178%

    No Known Activations