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

    Neuronpedia

    INDEX
    Explanations

    phrases that emphasize or introduce a specific statement or topic

    oai_token-act-pair · gpt-3.5-turbo

    a specific character or string that is frequently repeated in phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Drawn
    -0.82
     vulner
    -0.75
     Antar
    -0.74
     Mobil
    -0.67
     Belfast
    -0.66
     sacrific
    -0.64
     Agric
    -0.64
     Gardens
    -0.63
     ropes
    -0.62
     printers
    -0.60
    POSITIVE LOGITS
    same
    0.96
    ï¸ı
    0.96
    fter
    0.92
    href
    0.91
    ski
    0.89
    Pg
    0.89
    shall
    0.83
    felt
    0.81
    few
    0.80
    mir
    0.79
    Act Density 0.086%

    No Known Activations