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

    Neuronpedia

    INDEX
    Explanations

    sports-related terms and actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to ongoing events or actions in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     issu
    -0.65
    Methods
    -0.65
    RO
    -0.64
     Rewards
    -0.64
    Higher
    -0.63
    rw
    -0.62
     Subjects
    -0.62
    ept
    -0.61
     discrep
    -0.59
     abstract
    -0.57
    POSITIVE LOGITS
     Jr
    0.82
     famously
    0.80
     tweeting
    0.76
    ogun
    0.75
    sels
    0.72
    cussion
    0.70
    SON
    0.68
     whom
    0.67
    tsky
    0.67
    icz
    0.66
    Act Density 0.561%

    No Known Activations