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

    Neuronpedia

    INDEX
    Explanations

    names or terms containing the substring "j"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the character "j" in various contexts throughout the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lauder
    -0.73
     dispers
    -0.70
     bleach
    -0.67
    holder
    -0.67
    BALL
    -0.65
     dictators
    -0.63
    holders
    -0.63
     rooting
    -0.63
     dispersed
    -0.62
     Soccer
    -0.62
    POSITIVE LOGITS
    ournals
    1.37
    acket
    1.27
    ealous
    1.24
    itsu
    1.21
    unction
    1.20
    utsu
    1.17
    oint
    1.12
    ourn
    1.12
    unal
    1.12
    ordan
    1.11
    Act Density 0.031%

    No Known Activations