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

    Neuronpedia

    INDEX
    Explanations

    phrases associated with validity and assessment in a research context

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

    after "with" or ")"

    np_acts-logits-general · gemini-2.0-flash

    testing and planning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     everything
    -0.35
    워
    -0.34
    everything
    -0.33
    Everything
    -0.32
     Miko
    -0.29
    As
    -0.28
    miyorum
    -0.27
     så
    -0.27
    PO
    -0.27
    ポ
    -0.27
    POSITIVE LOGITS
     незавершена
    0.78
    دانشنامهٔ
    0.75
    windowFixed
    0.74
    parsedMessage
    0.72
     Roskov
    0.68
     témoig
    0.66
    adpleegd
    0.66
     Infór
    0.65
    новниш
    0.63
     мәкал
    0.61
    Act Density 0.895%

    No Known Activations