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

    Neuronpedia

    INDEX
    Explanations

    verbs expressing a strong level of certainty or likelihood

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "be."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pwr
    -0.62
     rollout
    -0.60
    uez
    -0.59
     RELEASE
    -0.58
    hra
    -0.57
     Soon
    -0.57
    errilla
    -0.56
     hurry
    -0.56
    ¶
    -0.55
     Currently
    -0.55
    POSITIVE LOGITS
     construed
    1.51
     interpreted
    1.46
     termed
    1.27
     likened
    1.25
     viewed
    1.25
     regarded
    1.25
     considered
    1.24
     summed
    1.19
     categorized
    1.19
     attributed
    1.18
    Act Density 0.128%

    No Known Activations