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

    Neuronpedia

    INDEX
    Explanations

    verbs related to initiating, influencing, or impacting

    oai_token-act-pair · gpt-3.5-turbo

    verbs associated with change or transformation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     challeng
    -0.67
     charism
    -0.66
     surv
    -0.61
     nutshell
    -0.59
     ende
    -0.58
     sul
    -0.57
     reper
    -0.57
     crawl
    -0.57
     describ
    -0.56
     quir
    -0.56
    POSITIVE LOGITS
    ing
    1.83
    ING
    1.28
    ingly
    1.20
    ed
    1.17
    ring
    1.16
    ioned
    1.09
    edIn
    1.04
    iving
    1.04
    ming
    1.01
    eering
    1.00
    Act Density 0.133%

    No Known Activations