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

    Neuronpedia

    INDEX
    Explanations

    locations or positions in a sequence or physical space

    oai_token-act-pair · gpt-3.5-turbo

    the word "somewhere" or its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iff
    -0.82
    ulators
    -0.71
    icer
    -0.70
    eh
    -0.69
    ducers
    -0.68
    DOM
    -0.67
    ann
    -0.66
    ude
    -0.65
    abilities
    -0.64
    raid
    -0.64
    POSITIVE LOGITS
     else
    1.43
    Else
    1.41
     Else
    1.07
    abouts
    0.88
    else
    0.85
    ãĤ´ãĥ³
    0.82
    ĪĴ
    0.75
     unpop
    0.74
     unspecified
    0.74
     Somewhere
    0.71
    Act Density 0.016%

    No Known Activations