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

    Neuronpedia

    INDEX
    Explanations

    adjectives describing qualities with varying levels of intensity

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with legal or reputational implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uers
    -0.63
     Parables
    -0.61
    ©¶æ
    -0.58
    ivalry
    -0.57
    "},
    -0.57
    aturdays
    -0.55
    Pacific
    -0.54
    ools
    -0.54
    «ĺ
    -0.54
     Springer
    -0.54
    POSITIVE LOGITS
    )
    1.45
    ?)
    1.33
    -)
    1.26
    )-
    1.24
    !)
    1.22
    )'
    1.21
    )!
    1.18
    *)
    1.13
    )?
    1.06
    )—
    1.05
    Act Density 0.302%

    No Known Activations