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

    Neuronpedia

    INDEX
    Explanations

    phrases describing or recounting events and actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "described" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alde
    -0.67
     surpassed
    -0.63
    valid
    -0.61
    ãģ¨
    -0.61
    aceous
    -0.60
    ï¸ı
    -0.60
    iest
    -0.60
    ãĥ©
    -0.60
    Phys
    -0.59
    fort
    -0.59
    POSITIVE LOGITS
    igate
    0.84
    igating
    0.84
    igated
    0.78
    artz
    0.75
     himself
    0.73
     difficulties
    0.70
     themselves
    0.66
     him
    0.65
     herself
    0.65
     similarities
    0.64
    Act Density 0.081%

    No Known Activations