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

    Neuronpedia

    INDEX
    Explanations

    elements related to influence and power dynamics

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

    influential and important words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.57
    PyTuple
    -0.47
    sbericht
    -0.47
    灵感
    -0.40
    orney
    -0.40
     tetap
    -0.39
     freuen
    -0.38
    piecze
    -0.37
     freue
    -0.37
     ची
    -0.37
    POSITIVE LOGITS
    important
    0.57
     influential
    0.56
     important
    0.53
    principalColumn
    0.51
    重要
    0.50
    UseVisualStyle
    0.48
    ValueStyle
    0.47
     utafitiHapana
    0.47
    artifactId
    0.46
    AutoField
    0.46
    Act Density 0.096%

    No Known Activations