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

    Neuronpedia

    INDEX
    Explanations

    locations or geographical names

    oai_token-act-pair · gpt-3.5-turbo

    colons in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilater
    -0.87
     recip
    -0.85
    stairs
    -0.66
    halla
    -0.65
    teness
    -0.64
    Roaming
    -0.63
    iqueness
    -0.62
    lvl
    -0.61
    igue
    -0.60
    agonal
    -0.60
    POSITIVE LOGITS
     Thousands
    0.82
     Riding
    0.81
     Dozens
    0.77
     Ahead
    0.75
     Latest
    0.74
     Yesterday
    0.73
     Hundreds
    0.70
     Newly
    0.69
     Following
    0.68
     Former
    0.66
    Act Density 0.027%

    No Known Activations