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

    Neuronpedia

    INDEX
    Explanations

    phrases related to transformation or change

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to transformation or change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    è¦ļéĨĴ
    -0.73
    cade
    -0.64
    ority
    -0.60
    llah
    -0.59
    ept
    -0.58
    fters
    -0.58
     challenger
    -0.58
    irms
    -0.58
    mma
    -0.58
    arers
    -0.58
    POSITIVE LOGITS
     into
    0.75
    coat
    0.73
     tide
    0.71
    around
    0.70
     Tide
    0.66
    Ī
    0.66
    ħ
    0.65
     Into
    0.64
     INTO
    0.62
     tides
    0.62
    Act Density 0.058%

    No Known Activations