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

    Neuronpedia

    INDEX
    Explanations

    repeated instances of the variable identifier "tmp" in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    temporary files and directories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pleaſure
    -0.65
     poffe
    -0.55
     houſe
    -0.54
     itſelf
    -0.54
     cauſe
    -0.53
    on
    -0.51
    <bos>
    -0.50
     Houſe
    -0.48
    ells
    -0.47
    arent
    -0.47
    POSITIVE LOGITS
     tmp
    1.70
    tmp
    1.54
    Tmp
    1.27
     TMP
    1.05
    TMP
    1.00
    tmpl
    0.87
    tmpdir
    0.76
     Tm
    0.72
     Tom
    0.68
     Temporary
    0.66
    Act Density 0.008%

    No Known Activations