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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to brightness or positive illumination

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilet
    -0.15
    plevel
    -0.15
    nd
    -0.14
    ches
    -0.14
    ese
    -0.14
    ripp
    -0.14
    AndPassword
    -0.14
    ional
    -0.14
    moz
    -0.14
    ÙĬØ©
    -0.14
    POSITIVE LOGITS
    -eyed
    0.16
    -light
    0.16
    -haired
    0.15
    ãĥ«ãĥī
    0.15
    rier
    0.15
    light
    0.14
    point
    0.14
     ctypes
    0.14
    inati
    0.14
    ingly
    0.13
    Act Density 0.078%

    No Known Activations