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

    Neuronpedia

    INDEX
    Explanations

    Names related to political figures

    oai_token-act-pair · gpt-3.5-turbo

    names associated with individuals involved in legal or controversial situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ANGE
    -0.80
    lessly
    -0.78
    lander
    -0.72
    ENTS
    -0.62
    SET
    -0.62
     Child
    -0.61
    CEPT
    -0.58
    trap
    -0.58
     Ops
    -0.58
    prints
    -0.58
    POSITIVE LOGITS
    areth
    1.04
    imir
    0.91
    olin
    0.84
    amara
    0.83
    aji
    0.83
    phe
    0.81
    itas
    0.81
    eless
    0.80
    aren
    0.79
    isphere
    0.79
    Act Density 0.088%

    No Known Activations