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

    Neuronpedia

    INDEX
    Explanations

    conversational phrases indicating requests for information or assistance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Annahme
    -0.50
    aryti
    -0.45
    farwyddwr
    -0.45
    つも
    -0.44
     resourceCulture
    -0.43
    })();
    -0.43
     GenerationType
    -0.43
    IPA
    -0.42
    IUrlHelper
    -0.42
    MIDDLEWARE
    -0.41
    POSITIVE LOGITS
     tell
    1.97
     telling
    1.90
     explain
    1.81
     explaining
    1.73
    Tell
    1.71
     Tell
    1.70
     tells
    1.67
     Telling
    1.62
     told
    1.61
     TELL
    1.61
    Act Density 1.238%

    No Known Activations