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

    Neuronpedia

    INDEX
    Explanations

    sentences with high emotional impact or significant narrative importance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    \{\\
    -0.88
    ...');
    -0.72
    ...");
    -0.70
    ...");
    -0.63
    rungsseite
    -0.63
    IonicModule
    -0.62
    .*")]
    -0.61
    ...";
    -0.58
    ?");
    -0.57
    ...')
    -0.57
    POSITIVE LOGITS
     —
    2.58
     –
    2.57
     -
    2.47
    —
    2.41
     --
    2.30
    –
    2.22
    --
    2.14
     −
    2.03
    ——
    2.02
    －
    2.00
    Act Density 0.988%

    No Known Activations