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

    Neuronpedia

    INDEX
    Explanations

    the verb "making" in various forms and contexts

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

    describing actions and their results

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ſtate
    -0.67
     houſe
    -0.63
     ſche
    -0.63
     Houſe
    -0.59
    ähteet
    -0.59
     gräns
    -0.59
    følgelig
    -0.56
    şört
    -0.56
     ſie
    -0.55
    arangay
    -0.55
    POSITIVE LOGITS
    Making
    1.44
     Making
    1.43
    making
    1.34
     MAKING
    1.26
     making
    1.26
    MAKING
    1.23
     makin
    0.77
    aking
    0.76
    ing
    0.76
    doing
    0.71
    Act Density 0.011%

    No Known Activations