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

    Neuronpedia

    INDEX
    Explanations

    technical terms and commands related to programming and system operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ness
    -0.29
    sWith
    -0.20
    nya
    -0.20
    lify
    -0.19
    shot
    -0.18
    ishly
    -0.18
    smith
    -0.18
    set
    -0.18
    lights
    -0.18
    si
    -0.18
    POSITIVE LOGITS
    able
    0.32
    ments
    0.26
    ABLE
    0.23
    ability
    0.23
    cation
    0.22
    ables
    0.22
    urope
    0.22
    MENT
    0.22
    MENTS
    0.21
    -your
    0.21
    Act Density 0.215%

    No Known Activations