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

    Neuronpedia

    INDEX
    Explanations

    proper names, specifically focusing on the name "Erik" and "Felix" with various numbers associated with the activations

    oai_token-act-pair · gpt-3.5-turbo

    the name "Erik" and related prominent names in the context of specific events or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    schild
    -0.78
     Decay
    -0.77
     ACTIONS
    -0.72
    tool
    -0.71
    roads
    -0.68
    Gh
    -0.68
    scape
    -0.67
    MX
    -0.67
    MQ
    -0.66
    align
    -0.66
    POSITIVE LOGITS
    ongyang
    0.87
    yip
    0.83
    abba
    0.78
    nesday
    0.77
    vernment
    0.76
    Ń·
    0.76
    doms
    0.75
    irit
    0.74
    rious
    0.73
    jri
    0.73
    Act Density 0.060%

    No Known Activations