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

    Neuronpedia

    INDEX
    Explanations

    names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    repeated instances of a specific name or term

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãģ¦
    -0.89
     Yel
    -0.80
    ces
    -0.74
     GEAR
    -0.70
     exha
    -0.70
     Lyft
    -0.70
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.69
    ggies
    -0.68
     genital
    -0.67
     Coyotes
    -0.66
    POSITIVE LOGITS
    mann
    1.03
    ronics
    0.98
    cht
    0.92
    geist
    0.91
    ung
    0.85
    alion
    0.85
    ohl
    0.82
    igger
    0.81
    leness
    0.81
    robe
    0.81
    Act Density 0.007%

    No Known Activations