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

    Neuronpedia

    INDEX
    Explanations

    emotional or impactful statements relating to personal experiences and significant societal themes

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

    words and phrases related to quantitative limits, boundaries, or numerical constraints.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Negative Logits
     –,
    -0.99
     —,
    -0.73
     -,
    -0.67
    —,
    -0.63
     Normdatei
    -0.57
    ,:),
    -0.51
    ","");
    -0.51
    ▬▬
    -0.51
    …,
    -0.50
     />,
    -0.50
    POSITIVE LOGITS
    .
    0.84
    ;
    0.51
    InjectAttribute
    0.43
    Ex
    0.42
    Itoa
    0.36
    Derbyniad
    0.36
     It
    0.36
    De
    0.36
     Ex
    0.35
    <eos>
    0.33
    Act Density 0.823%

    No Known Activations