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

    Neuronpedia

    INDEX
    Explanations

    concepts related to community, values, and equity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ^^
    -0.15
     amplify
    -0.14
    otton
    -0.14
    .squeeze
    -0.14
    _clock
    -0.14
    achen
    -0.13
    .jetbrains
    -0.13
    roker
    -0.13
     lif
    -0.13
    olve
    -0.13
    POSITIVE LOGITS
     inform
    0.60
     informs
    0.54
     Inform
    0.53
    inform
    0.52
     informed
    0.52
     informing
    0.52
    Inform
    0.50
     shape
    0.43
     shapes
    0.41
     shaped
    0.40
    Act Density 0.362%

    No Known Activations