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

    Neuronpedia

    INDEX
    Explanations

    references to global events or entities

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "world" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imon
    -0.98
    veyard
    -0.88
    ippi
    -0.84
    »Ĵ
    -0.71
    andre
    -0.70
    aleb
    -0.69
    haps
    -0.69
    Initialized
    -0.68
    ema
    -0.68
    drawn
    -0.68
    POSITIVE LOGITS
     premiere
    0.86
    wide
    0.82
    liness
    0.82
     economy
    0.81
     proletariat
    0.80
     renowned
    0.76
    osphere
    0.71
    wake
    0.70
     warming
    0.70
    scape
    0.69
    Act Density 0.071%

    No Known Activations