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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "never" and its surrounding context in relation to experiences or actions

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

    never before

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    awtextra
    -0.47
     Wikimedijinoj
    -0.45
    createStatement
    -0.44
    GTCX
    -0.44
    makeConstraints
    -0.43
    AnchorStyles
    -0.43
    ölkerung
    -0.43
    enumii
    -0.43
    Xna
    -0.43
     occaf
    -0.42
    POSITIVE LOGITS
    AutoScaleMode
    0.50
     ever
    0.47
     EVER
    0.47
     any
    0.47
     nus
    0.45
    Bibliograf
    0.44
     jemals
    0.43
     Bux
    0.41
     ANY
    0.41
     anything
    0.40
    Act Density 0.035%

    No Known Activations