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

    Neuronpedia

    INDEX
    Explanations

    terms related to adaptability and adjustment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anj
    -0.16
    iegel
    -0.15
    /MPL
    -0.15
    ãĥ©ãĥĥãĤ¯
    -0.15
    agn
    -0.14
    Gesture
    -0.14
    reat
    -0.14
    üny
    -0.13
    flo
    -0.13
    ienes
    -0.13
    POSITIVE LOGITS
    yre
    0.16
    uzey
    0.14
    bourne
    0.14
    uby
    0.14
     Blind
    0.14
    orges
    0.14
    chal
    0.14
    áng
    0.14
    kker
    0.14
    apas
    0.13
    Act Density 0.007%

    No Known Activations