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

    Neuronpedia

    INDEX
    Explanations

    references to specific locations and regions

    oai_token-act-pair · gpt-3.5-turbo

    the definite article "the"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    roup
    -0.84
    itatively
    -0.78
    chery
    -0.77
    athered
    -0.76
    arily
    -0.72
    omas
    -0.72
    bands
    -0.70
    rift
    -0.69
    orously
    -0.68
    nil
    -0.67
    POSITIVE LOGITS
    Ò
    0.74
     Diabetes
    0.70
     Thumbnails
    0.67
     Minotaur
    0.66
    ħĭ
    0.66
    âĸ¬
    0.66
     Ruk
    0.66
     Administ
    0.65
     Twist
    0.63
     Cookie
    0.63
    Act Density 0.000%

    No Known Activations