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

    Neuronpedia

    INDEX
    Explanations

    instances where the text discusses ability or possibility

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "can" in various contexts, indicating ability or possibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ULTS
    -0.67
    soever
    -0.67
     spoilers
    -0.65
    senal
    -0.64
     Actions
    -0.63
     reflections
    -0.62
     Falling
    -0.62
     Strikes
    -0.61
    quartered
    -0.60
     Sands
    -0.60
    POSITIVE LOGITS
    't
    1.52
     afford
    1.43
     convince
    1.11
     persuade
    1.01
     muster
    1.00
     manage
    0.96
     reliably
    0.93
    adian
    0.92
     tolerate
    0.89
     find
    0.89
    Act Density 0.103%

    No Known Activations