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

    Neuronpedia

    INDEX
    Explanations

    scientific terms related to materials and substances

    oai_token-act-pair · gpt-3.5-turbo

    words associated with metrics and classification systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     innocence
    -0.70
     Hobbit
    -0.69
     peek
    -0.64
    hood
    -0.62
     envelope
    -0.60
     goblin
    -0.59
     Mahjong
    -0.59
     Cinderella
    -0.59
    keepers
    -0.59
     libel
    -0.58
    POSITIVE LOGITS
    ritic
    0.96
    urgy
    0.86
    opol
    0.83
    ãĤ¡
    0.80
    xual
    0.78
    OG
    0.78
    andum
    0.77
    OLOG
    0.76
    urgical
    0.76
    ALLY
    0.75
    Act Density 0.081%

    No Known Activations