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

    Neuronpedia

    INDEX
    Explanations

    occurrences of falling or descending

    oai_token-act-pair · gpt-3.5-turbo

    situations involving falls or accidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uncture
    -0.78
    otide
    -0.71
    actionDate
    -0.70
    algia
    -0.69
    PN
    -0.69
     saliva
    -0.68
    ufact
    -0.68
    ffect
    -0.67
    ochemistry
    -0.67
    earcher
    -0.67
    POSITIVE LOGITS
     cliffs
    1.49
     tallest
    1.47
     stairs
    1.35
     skysc
    1.33
     ceilings
    1.30
     cliff
    1.30
     tower
    1.25
     heights
    1.25
     towering
    1.21
     towers
    1.21
    Act Density 0.309%

    No Known Activations