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

    Neuronpedia

    INDEX
    Explanations

    customer service-oriented phrases indicating assistance and responsiveness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Future actions involving "will" or "can"

    np_acts-logits-general · gemini-2.0-flash

    offering future assistance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ########.
    -0.52
     <>",
    -0.49
    TagHelper
    -0.49
    cipient
    -0.47
     incipient
    -0.46
    KEYCODE
    -0.46
    endphp
    -0.46
     المعيارى
    -0.45
    MigrationBuilder
    -0.44
    ValueStyle
    -0.44
    POSITIVE LOGITS
    IVEREF
    0.40
    帮你
    0.38
     help
    0.38
    为你
    0.38
     meteoro
    0.38
     felizes
    0.38
     will
    0.37
     étoit
    0.37
     mercancías
    0.36
    DispatchToProps
    0.36
    Act Density 0.102%

    No Known Activations