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

    Neuronpedia

    INDEX
    Explanations

    introductory phrases or sequences that indicate a list or order of information

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

    Sentences that begin with "First"

    np_acts-logits-general · gemini-2.0-flash

    the first point

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AndEndTag
    -1.02
     houſe
    -0.93
     purpoſe
    -0.90
     Houſe
    -0.90
     photolibrary
    -0.89
     myſelf
    -0.88
     alfo
    -0.88
    tvguidetime
    -0.87
     Efq
    -0.86
     Shakspeare
    -0.86
    POSITIVE LOGITS
    ,
    0.79
     off
    0.78
     we
    0.70
     thing
    0.69
     most
    0.59
    off
    0.59
     let
    0.57
     اینکه
    0.57
    most
    0.56
     you
    0.53
    Act Density 0.143%

    No Known Activations