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

    Neuronpedia

    INDEX
    Explanations

    coding-related terms and indicators of functionality or state changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hamp
    -0.15
    xes
    -0.15
    oreach
    -0.15
    enstein
    -0.15
    ме
    -0.14
    awner
    -0.14
    dds
    -0.14
    ¼åIJĪ
    -0.14
    slashes
    -0.14
    929
    -0.14
    POSITIVE LOGITS
    osa
    0.15
     fkk
    0.15
    oun
    0.14
     prop
    0.14
    fet
    0.14
     ComVisible
    0.14
    cone
    0.13
    press
    0.13
    _DC
    0.13
    obel
    0.13
    Act Density 0.081%

    No Known Activations