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

    Neuronpedia

    INDEX
    Explanations

    Phrases related to security or encryption protocols

    oai_token-act-pair · gpt-3.5-turbo

    references to the "PG" (presumably parental guidance) rating system

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ufact
    -0.78
     Ic
    -0.74
    cles
    -0.73
    fact
    -0.73
    joined
    -0.70
    bridge
    -0.68
     Bones
    -0.68
    izen
    -0.64
     Horizons
    -0.63
    footed
    -0.63
    POSITIVE LOGITS
    ENE
    0.93
    raph
    0.87
    ENC
    0.86
    PI
    0.86
    omez
    0.86
    asus
    0.86
    osate
    0.85
    raphic
    0.84
    allery
    0.83
    iants
    0.80
    Act Density 0.033%

    No Known Activations