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

    Neuronpedia

    INDEX
    Explanations

    instances of actions or events happening

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of actions and interactions involving characters in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    conservancy
    -0.68
    unless
    -0.64
    uably
    -0.62
    ©¶æ¥µ
    -0.61
    fleet
    -0.61
    avid
    -0.60
     Historically
    -0.60
    absolutely
    -0.59
    ãĥIJ
    -0.58
    ribe
    -0.58
    POSITIVE LOGITS
     finished
    0.95
     completion
    0.85
     completes
    0.81
    ward
    0.79
     arrival
    0.74
     expiration
    0.73
     arrives
    0.73
     returned
    0.70
     completed
    0.70
     expires
    0.70
    Act Density 0.348%

    No Known Activations