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

    Neuronpedia

    INDEX
    Explanations

    words related to politics and local issues

    oai_token-act-pair · gpt-3.5-turbo

    instances of the letter 'L' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Maced
    -0.70
     JPEG
    -0.63
     Alban
    -0.62
     Mobil
    -0.61
     scram
    -0.60
     Mirage
    -0.59
     Axel
    -0.58
     Prescott
    -0.57
     Tanz
    -0.57
     Pap
    -0.56
    POSITIVE LOGITS
    TION
    0.86
    ï¸ı
    0.85
    sure
    0.79
    ski
    0.76
    forcing
    0.76
    ï¸
    0.75
    egal
    0.74
    swer
    0.73
    rency
    0.71
    agree
    0.71
    Act Density 0.284%

    No Known Activations