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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the progression or unfolding of events

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the unfolding or progression of events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antry
    -0.76
    asus
    -0.75
    cius
    -0.72
    aints
    -0.72
    oppy
    -0.69
    avorite
    -0.68
     Primordial
    -0.68
    shaw
    -0.67
    cious
    -0.66
    anan
    -0.66
    POSITIVE LOGITS
    fitted
    0.89
     differently
    0.82
    flows
    0.81
    uate
    0.75
    flow
    0.73
    wards
    0.73
    casts
    0.72
    olate
    0.70
     exactly
    0.69
    skirts
    0.68
    Act Density 0.041%

    No Known Activations