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

    Neuronpedia

    INDEX
    Explanations

    phrases starting with "Depending on"

    oai_token-act-pair · gpt-3.5-turbo

    conditional phrases or statements that highlight dependency on various factors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vision
    -0.90
    code
    -0.76
    posted
    -0.75
    blue
    -0.74
    talk
    -0.74
    se
    -0.74
    mark
    -0.73
    anas
    -0.72
     Gone
    -0.72
    NER
    -0.71
    POSITIVE LOGITS
     conting
    0.74
     arrang
    0.73
     facult
    0.71
     upon
    0.71
     occas
    0.70
     unden
    0.70
     circumst
    0.69
     depending
    0.68
     degrees
    0.68
     amounts
    0.68
    Act Density 0.013%

    No Known Activations