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

    Neuronpedia

    INDEX
    Explanations

    pronouns like 'we' and 'I' followed by present tense verbs

    oai_token-act-pair · gpt-3.5-turbo

    contractions and forms of the verb "to be" that indicate existence or state

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    =-=-
    -0.77
    urrencies
    -0.67
    clerosis
    -0.67
    士
    -0.67
     Stability
    -0.66
    姫
    -0.64
     Kills
    -0.62
    inventoryQuantity
    -0.62
    ggles
    -0.62
     misplaced
    -0.60
    POSITIVE LOGITS
     doing
    1.21
     aiming
    1.14
     trying
    1.12
     expecting
    1.11
     proposing
    1.10
     hoping
    1.10
     experiencing
    1.09
     attempting
    1.08
     striving
    1.07
     undertaking
    1.05
    Act Density 0.112%

    No Known Activations