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

    Neuronpedia

    INDEX
    Explanations

    mentions of tangible objects or resources

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "material" and variations associated with it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Barth
    -0.69
    ort
    -0.65
     Jed
    -0.65
     Bass
    -0.65
     Hatch
    -0.64
     bitters
    -0.64
    IELD
    -0.64
    ARP
    -0.63
     Breaker
    -0.62
     Pis
    -0.61
    POSITIVE LOGITS
    ity
    0.94
    izes
    0.93
    istic
    0.92
    utonium
    0.90
    ized
    0.89
    estine
    0.88
     possessions
    0.86
    izing
    0.86
    istically
    0.86
    isations
    0.85
    Act Density 0.023%

    No Known Activations