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

    Neuronpedia

    INDEX
    Explanations

    phrases or words related to correctness, appropriateness, or optimization

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "right" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.76
    anned
    -0.74
    cit
    -0.72
    ipolar
    -0.65
     conclud
    -0.65
    ADRA
    -0.65
    bery
    -0.64
    SEE
    -0.63
    76561
    -0.62
    lua
    -0.62
    POSITIVE LOGITS
    eous
    0.90
     wing
    0.90
     thing
    0.82
     amount
    0.77
     answer
    0.75
     hemisphere
    0.75
     side
    0.74
     way
    0.73
     ballpark
    0.72
     person
    0.72
    Act Density 0.043%

    No Known Activations