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

    Neuronpedia

    INDEX
    Explanations

    phrases reflecting regret or personal dilemmas

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

    often followed by negation

    np_acts-logits-general · gemini-2.0-flash

    Input decoration and sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     elites
    -0.64
     incentiv
    -0.61
     nuanced
    -0.60
     impactful
    -0.60
     silhouettes
    -0.60
     relatable
    -0.59
     crafted
    -0.59
     prioriti
    -0.59
     elite
    -0.58
    fue
    -0.57
    POSITIVE LOGITS
    SequentialGroup
    0.38
    StoryboardSegue
    0.34
     !_
    0.32
    ="@+
    0.32
     ${({
    0.30
     ***!
    0.30
     getColumn
    0.29
    0.29
     muß
    0.28
     InputDecoration
    0.28
    Act Density 0.329%

    No Known Activations