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

    Neuronpedia

    INDEX
    Explanations

    expressions of exploitation and legal concerns related to personal or societal issues

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

    preceding "as" in comparisons or descriptions

    np_acts-logits-general · gemini-2.0-flash

    performance comparison advertising profit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     propOrder
    -0.95
     Shakspeare
    -0.75
     myſelf
    -0.74
    SerializedName
    -0.74
     Efq
    -0.72
    ValueStyle
    -0.72
     purpoſe
    -0.72
     Theſe
    -0.71
     pleaſure
    -0.71
    findpost
    -0.70
    POSITIVE LOGITS
     very
    1.03
     able
    0.95
     extremely
    0.90
     a
    0.85
     highly
    0.85
     quite
    0.82
     difficult
    0.81
     an
    0.81
     easy
    0.76
     aware
    0.76
    Act Density 0.507%

    No Known Activations