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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "to" in various contexts, particularly when it expresses positivity or reassurance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mint
    -0.16
    ayment
    -0.15
    .Views
    -0.14
    _DUMP
    -0.14
     Nam
    -0.14
     enjoyment
    -0.14
    Understanding
    -0.13
     convention
    -0.13
     Understanding
    -0.13
    ina
    -0.13
    POSITIVE LOGITS
     hear
    0.23
     see
    0.22
     finally
    0.20
    finally
    0.18
    see
    0.18
     Hear
    0.17
     note
    0.16
    hear
    0.16
     sees
    0.16
    quier
    0.15
    Act Density 0.039%

    No Known Activations