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

    Neuronpedia

    INDEX
    Explanations

    phrases related to making the world a better place

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "world" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sbm
    -0.89
    imon
    -0.84
    veyard
    -0.84
    ippi
    -0.82
    uckle
    -0.78
    omething
    -0.76
    »Ĵ
    -0.75
    ividual
    -0.73
     unfocusedRange
    -0.70
    EStream
    -0.69
    POSITIVE LOGITS
     economy
    1.01
    liness
    0.90
    wide
    0.85
    osphere
    0.84
    scape
    0.83
     premiere
    0.82
     proletariat
    0.82
    's
    0.79
     Economy
    0.77
    building
    0.76
    Act Density 0.066%

    No Known Activations