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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names of individuals or locations

    oai_token-act-pair · gpt-3.5-turbo

    words related to age or aging

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pradesh
    -0.65
    worldly
    -0.62
    iaries
    -0.61
    ourced
    -0.60
     blob
    -0.58
     Dragonbound
    -0.57
     "$:/
    -0.57
    oros
    -0.57
     symm
    -0.56
     transitional
    -0.56
    POSITIVE LOGITS
    llan
    1.02
    ño
    0.93
    witz
    0.86
    bee
    0.85
    ll
    0.84
    tta
    0.80
    y
    0.78
    e
    0.76
    lett
    0.76
    tell
    0.75
    Act Density 0.102%

    No Known Activations