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

    Neuronpedia

    INDEX
    Explanations

    words related to directions or locations

    oai_token-act-pair · gpt-3.5-turbo

    sequences of characters or unusual text formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sabha
    -0.72
     corrections
    -0.68
     GPS
    -0.68
     WhatsApp
    -0.67
     Pradesh
    -0.66
     Gmail
    -0.65
     radar
    -0.64
     Amit
    -0.63
     Morse
    -0.62
     extrap
    -0.62
    POSITIVE LOGITS
    dro
    0.93
    sure
    0.86
    ¢
    0.82
    say
    0.79
    £
    0.79
    Ĵ
    0.78
    should
    0.76
    º
    0.76
    ¡
    0.75
    ser
    0.74
    Act Density 0.418%

    No Known Activations