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

    Neuronpedia

    INDEX
    Explanations

    specific technical terms and metrics related to measurements and data analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bat
    -0.15
    fect
    -0.14
     Nu
    -0.14
    -LAST
    -0.14
    éĢļ
    -0.14
     Mi
    -0.14
     LOC
    -0.14
    -ves
    -0.14
     slee
    -0.13
    ัà¸Ķ
    -0.13
    POSITIVE LOGITS
    ml
    0.25
    Gl
    0.25
    WN
    0.24
    WF
    0.23
    GV
    0.23
    GF
    0.23
    WR
    0.22
    XR
    0.22
    29
    0.22
    mx
    0.22
    Act Density 0.003%

    No Known Activations