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

    Neuronpedia

    INDEX
    Explanations

    phrases related to potential or inevitable events or situations

    oai_token-act-pair · gpt-3.5-turbo

    references to likelihood or occurrences of events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reviewer
    -0.82
    ilts
    -0.65
    quartered
    -0.63
    çīĪ
    -0.62
     slots
    -0.62
    endment
    -0.61
     praises
    -0.61
    atography
    -0.60
     holdings
    -0.59
    agall
    -0.58
    POSITIVE LOGITS
     happening
    1.78
     happen
    1.67
     occurring
    1.66
     happened
    1.42
     occur
    1.37
     happens
    1.34
     occurrence
    1.28
     perpetrated
    1.26
     occurrences
    1.26
    occ
    1.23
    Act Density 0.492%

    No Known Activations