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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and variations of stress in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ↵↵
    -0.36
    }")]
    -0.35
    ↵↵↵
    -0.32
     movement
    -0.29
     --}}
    -0.28
     following
    -0.28
    ())));
    -0.28
    ()}}
    -0.28
    ↵↵↵↵
    -0.26
    ↵
    -0.26
    POSITIVE LOGITS
    makeText
    0.74
     <<<<<<<<<<<<<<
    0.71
    awtextra
    0.70
    TagHelper
    0.68
    دانشنامهٔ
    0.65
    المناصب
    0.65
    ſicht
    0.64
    GEBURTSDATUM
    0.64
     يتيمه
    0.63
    wiliwch
    0.63
    Act Density 0.104%

    No Known Activations