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

    Neuronpedia

    INDEX
    Explanations

    terms related to matching algorithms or criteria

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uen
    -0.16
    one
    -0.15
    LU
    -0.14
     cerv
    -0.14
    158
    -0.14
     Cant
    -0.14
     comple
    -0.14
    ain
    -0.14
     epoch
    -0.14
     tal
    -0.13
    POSITIVE LOGITS
    kus
    0.19
    ingly
    0.17
    yro
    0.17
    DispatchToProps
    0.16
    Ãłng
    0.15
    ories
    0.15
    ewood
    0.15
    nid
    0.14
    ogany
    0.14
    ÑĦи
    0.14
    Act Density 0.035%

    No Known Activations