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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating continuous or ongoing actions or situations

    oai_token-act-pair · gpt-3.5-turbo

    the recurrence of the word "throughout" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ggies
    -0.74
    ANS
    -0.72
    ku
    -0.66
    merga
    -0.64
    JV
    -0.64
    ifiable
    -0.63
    arial
    -0.62
     chops
    -0.60
    yah
    -0.60
    vir
    -0.59
    POSITIVE LOGITS
     eternity
    0.92
     history
    0.92
     much
    0.81
     Europe
    0.79
     adolescence
    0.78
     the
    0.77
     Asia
    0.73
     adulthood
    0.72
    estine
    0.72
     Southeast
    0.72
    Act Density 0.034%

    No Known Activations