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

    Neuronpedia

    INDEX
    Explanations

    words expressing strong opinions or calls to action

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

    Imperative verbs following "to"

    np_acts-logits-general · gemini-2.0-flash

    stop or shut

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ">//
    -0.69
    koli
    -0.54
     marty
    -0.52
     föruts
    -0.51
    openSession
    -0.50
    త్ర
    -0.50
     trygg
    -0.47
     bestens
    -0.46
     algod
    -0.45
     möjlighet
    -0.45
    POSITIVE LOGITS
     stop
    1.48
     Stop
    1.36
    Stop
    1.34
     shut
    1.34
    stop
    1.28
    Shut
    1.22
     STOP
    1.21
     Shut
    1.20
    shut
    1.19
     SHUT
    1.13
    Act Density 0.274%

    No Known Activations