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

    Neuronpedia

    INDEX
    Explanations

    adjectives or adverbs that convey certainty or definiteness

    oai_token-act-pair · gpt-3.5-turbo

    words associated with ambiguity and clarity in communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    udeb
    -0.84
    essed
    -0.74
    creen
    -0.69
    oresc
    -0.68
    othal
    -0.64
    opter
    -0.64
    ocket
    -0.63
    igraph
    -0.62
    omet
    -0.62
    afety
    -0.62
    POSITIVE LOGITS
    NESS
    0.87
    âĶĢâĶĢâĶĢâĶĢ
    0.85
    nesses
    0.85
    âĶĢâĶĢ
    0.78
    aneously
    0.77
    lihood
    0.77
     disadvantages
    0.77
    iencies
    0.76
    Ùħ
    0.72
     resemblance
    0.71
    Act Density 0.119%

    No Known Activations