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

    Neuronpedia

    INDEX
    Explanations

    references to divine entities and pronouns related to them

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

    he, him, his, she, they

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hangout
    -0.53
     funniest
    -0.52
     oddly
    -0.52
     anytime
    -0.52
    slick
    -0.51
     slick
    -0.51
    keits
    -0.51
     piggy
    -0.51
     hyped
    -0.50
    染
    -0.50
    POSITIVE LOGITS
     CURIAM
    0.49
     CreateTagHelper
    0.47
    0.46
     disegni
    0.40
    ImageContext
    0.40
     nothwendig
    0.39
     coloro
    0.38
    彼らは
    0.38
    makeText
    0.38
     species
    0.38
    Act Density 0.184%

    No Known Activations