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

    Neuronpedia

    INDEX
    Explanations

    adverbs used to express time or progression

    oai_token-act-pair · gpt-3.5-turbo

    the word "thus" and its variations or contextual uses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Defenders
    -0.68
     Polo
    -0.66
    igger
    -0.62
    GER
    -0.57
     Ones
    -0.57
    IG
    -0.56
    Õ
    -0.56
    ridges
    -0.56
     steroids
    -0.55
     metro
    -0.54
    POSITIVE LOGITS
    forth
    1.25
     far
    0.96
    entimes
    0.94
    ly
    0.90
    forward
    0.88
    far
    0.85
    cially
    0.76
    mask
    0.75
    lessly
    0.74
    tainment
    0.71
    Act Density 0.027%

    No Known Activations