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

    Neuronpedia

    INDEX
    Explanations

    references to prior discussions or pieces of writing

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

    a prior reference

    np_acts-logits-general · gemini-2.0-flash

    references to previous information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Administrativna
    -0.54
     wireType
    -0.47
    TemporalType
    -0.46
    Према
    -0.45
    dflare
    -0.45
    tagHelperRunner
    -0.43
    complexContent
    -0.42
    EndContext
    -0.41
    endphp
    -0.41
    ellido
    -0.41
    POSITIVE LOGITS
     earlier
    0.68
    earlier
    0.66
    previous
    0.64
     previous
    0.63
     previously
    0.62
     separate
    0.58
     Earlier
    0.57
    separate
    0.57
     précédemment
    0.56
    Earlier
    0.56
    Act Density 0.803%

    No Known Activations