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

    Neuronpedia

    INDEX
    Explanations

    future predictions or plans indicated by the verb "will" followed by an action

    oai_token-act-pair · gpt-3.5-turbo

    future actions or predictions regarding various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sandwich
    -0.61
    uces
    -0.60
    AAA
    -0.59
     conversions
    -0.58
    ONSORED
    -0.58
     exceeds
    -0.57
     occurred
    -0.57
    Rain
    -0.57
    ourke
    -0.56
    Awesome
    -0.56
    POSITIVE LOGITS
     doubtless
    1.42
     undoubtedly
    1.31
     need
    1.24
     surely
    1.20
     likely
    1.18
     gladly
    1.12
    need
    1.11
     argue
    1.08
     inevitably
    1.08
     reap
    1.07
    Act Density 0.173%

    No Known Activations