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

    Neuronpedia

    INDEX
    Explanations

    phrases related to accidentally discovering or encountering something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "stumble" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cers
    -0.73
    cius
    -0.73
    =#
    -0.67
    ²¾
    -0.67
    ciation
    -0.66
    cium
    -0.65
    tan
    -0.65
    scl
    -0.65
    nesota
    -0.65
    folios
    -0.64
    POSITIVE LOGITS
    weed
    0.99
     stumble
    0.83
    worthiness
    0.79
     stumbling
    0.77
    endor
    0.75
    own
    0.75
    Upon
    0.72
    bum
    0.70
    umble
    0.69
     stumbled
    0.68
    Act Density 0.044%

    No Known Activations