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

    Neuronpedia

    INDEX
    Explanations

    references to communication and requests for assistance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isy
    -0.17
    roys
    -0.15
    oleon
    -0.15
     è¡ĮæĶ¿
    -0.15
    ponse
    -0.15
    olleyError
    -0.14
    rame
    -0.14
    idth
    -0.14
    ocale
    -0.14
    ROKE
    -0.14
    POSITIVE LOGITS
    skirts
    0.16
    amel
    0.14
    bow
    0.13
    alink
    0.13
    meld
    0.13
    atrib
    0.13
    urm
    0.13
    ôi
    0.13
     Knights
    0.13
    uder
    0.13
    Act Density 0.232%

    No Known Activations