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

    Neuronpedia

    INDEX
    Explanations

    positive evaluations of performance or functionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unci
    -0.18
    agma
    -0.16
    anca
    -0.15
    dda
    -0.15
    uars
    -0.14
    ByExample
    -0.14
    obi
    -0.14
    Suppress
    -0.14
    uffed
    -0.14
    acs
    -0.14
    POSITIVE LOGITS
    缸
    0.17
     Copp
    0.15
    otion
    0.15
    SEL
    0.15
    äft
    0.14
    XT
    0.14
    å¡Ķ
    0.14
    instr
    0.14
    à¹Ħร
    0.13
    _DIP
    0.13
    Act Density 0.010%

    No Known Activations