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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to adjustment and modification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wich
    -0.17
    witch
    -0.16
    isci
    -0.16
    lÃŃÄį
    -0.16
    uem
    -0.16
    rud
    -0.16
    hurst
    -0.15
    nder
    -0.15
    chest
    -0.15
    anou
    -0.15
    POSITIVE LOGITS
    ments
    0.27
    ment
    0.22
    ors
    0.20
    ements
    0.19
    ement
    0.18
    asi
    0.18
    ably
    0.18
    ìĤ¬íķŃ
    0.17
    dictions
    0.16
    able
    0.16
    Act Density 0.016%

    No Known Activations