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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "mis" or variants thereof indicating mistakes or failures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ingly
    -0.15
     Ri
    -0.15
    æ¡ij
    -0.15
    -serif
    -0.15
    istically
    -0.14
    aved
    -0.14
    ajar
    -0.14
     Guerr
    -0.14
    ify
    -0.14
    orro
    -0.14
    POSITIVE LOGITS
    steps
    0.21
     mis
    0.20
     steps
    0.20
    step
    0.19
    emean
    0.19
     step
    0.19
    Steps
    0.17
     misd
    0.17
     Steps
    0.17
    STEP
    0.17
    Act Density 0.024%

    No Known Activations