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

    Neuronpedia

    INDEX
    Explanations

    the word "so", especially at the beginning of a sentence

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express conditional statements or hypothetical scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rals
    -0.72
     Faul
    -0.61
     Gaw
    -0.59
     burner
    -0.58
     Crack
    -0.58
     glances
    -0.57
    ر
    -0.56
     Flavoring
    -0.55
    ع
    -0.53
     flashbacks
    -0.53
    POSITIVE LOGITS
    oths
    1.16
    apy
    0.95
    bered
    0.91
    oner
    0.88
    iled
    0.85
    zin
    0.81
    iling
    0.81
    oooo
    0.80
    othes
    0.79
    othe
    0.79
    Act Density 0.065%

    No Known Activations