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

    Neuronpedia

    INDEX
    Explanations

    negative numerical values or indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imuth
    -0.15
    olds
    -0.15
    -0.14
     w
    -0.14
    rito
    -0.14
    969
    -0.14
    ghest
    -0.14
    å°ıå§IJ
    -0.13
    feat
    -0.13
    ember
    -0.13
    POSITIVE LOGITS
    +.
    0.18
    liv
    0.16
    iyas
    0.14
    iv
    0.14
     Alloy
    0.14
    ãĥ¼ãĥ
    0.14
    IDEO
    0.14
    à¸IJ
    0.14
    овиÑĩ
    0.13
    ouis
    0.13
    Act Density 0.034%

    No Known Activations