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

    Neuronpedia

    INDEX
    Explanations

    references to numerical values and indicators of ranking or classification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ignon
    -0.16
    yer
    -0.16
    aar
    -0.15
    oton
    -0.15
    elo
    -0.15
    æIJº
    -0.14
    Tiny
    -0.14
    oq
    -0.14
    amba
    -0.14
     mobil
    -0.14
    POSITIVE LOGITS
    isti
    0.17
     Ned
    0.17
    press
    0.16
    reh
    0.16
     Bundy
    0.16
    å§
    0.15
    acus
    0.15
     press
    0.15
    -h
    0.14
    eda
    0.14
    Act Density 0.039%

    No Known Activations