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

    Neuronpedia

    INDEX
    Explanations

    the phrase "type of" followed by a noun or noun phrase

    oai_token-act-pair · gpt-3.5-turbo

    references to various classifications or categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    姫
    -0.76
    pload
    -0.70
    romeda
    -0.70
     Rings
    -0.69
     Bots
    -0.69
    olulu
    -0.66
     Mald
    -0.65
     Kenya
    -0.64
    IRO
    -0.64
     Liberties
    -0.63
    POSITIVE LOGITS
    face
    1.26
    faces
    1.19
    etter
    1.03
    etting
    0.97
    casting
    0.93
    ahead
    0.84
    classes
    0.80
    olerance
    0.78
    lander
    0.77
    cast
    0.75
    Act Density 0.021%

    No Known Activations