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

    Neuronpedia

    INDEX
    Explanations

    comparisons that imply a disparity in expectations or experiences

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

    Personal pronouns followed by a verb of thought

    np_acts-logits-general · gemini-2.0-flash

    than expected or thought

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +#+
    -0.85
    MessageTagHelper
    -0.72
    enderror
    -0.63
     fotografico
    -0.63
     preghiera
    -0.63
     linguistique
    -0.63
     oublié
    -0.61
     kysy
    -0.60
     BoxDecoration
    -0.60
     chrétiens
    -0.59
    POSITIVE LOGITS
     imagined
    0.69
     anticipated
    0.68
     cherchés
    0.63
     expected
    0.62
     thought
    0.61
     hoped
    0.60
    想像
    0.59
     than
    0.59
     imagine
    0.56
    AccessorTable
    0.55
    Act Density 0.116%

    No Known Activations