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

    Neuronpedia

    INDEX
    Explanations

    instances of things falling or dropping from a height

    oai_token-act-pair · gpt-3.5-turbo

    references to significant falls or collapses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    actionDate
    -0.78
    relations
    -0.75
     seasoning
    -0.74
    gans
    -0.74
     microbi
    -0.71
    Ware
    -0.69
     fingerprint
    -0.69
    PN
    -0.68
     questionnaire
    -0.68
    iliate
    -0.67
    POSITIVE LOGITS
     cliffs
    1.40
     tallest
    1.34
     heights
    1.31
     towers
    1.30
     towering
    1.30
     skysc
    1.25
     ceilings
    1.24
     tower
    1.17
     ceiling
    1.16
     stairs
    1.15
    Act Density 0.638%

    No Known Activations