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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences referring to global or widespread concepts or events

    oai_token-act-pair · gpt-3.5-turbo

    references to "the world" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imon
    -0.87
    ippi
    -0.78
    veyard
    -0.77
    urations
    -0.76
    andre
    -0.75
    iar
    -0.74
     actionGroup
    -0.74
    irez
    -0.72
    ients
    -0.72
    ibility
    -0.71
    POSITIVE LOGITS
    wide
    0.89
     premiere
    0.86
    liness
    0.74
     Wide
    0.74
     wide
    0.73
     renowned
    0.72
     economy
    0.71
    building
    0.71
    Wide
    0.70
    wake
    0.70
    Act Density 0.058%

    No Known Activations