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

    Neuronpedia

    INDEX
    Explanations

    verbs related to creating, writing, sending, or making something

    oai_token-act-pair · gpt-3.5-turbo

    past tense verbs, particularly those indicating creation or action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ahon
    -0.59
     Metatron
    -0.59
    fts
    -0.57
    ctors
    -0.56
    enei
    -0.55
     vibrations
    -0.54
    maxwell
    -0.54
    physical
    -0.54
     faint
    -0.53
     Payton
    -0.53
    POSITIVE LOGITS
     beforehand
    1.06
     earlier
    0.90
     during
    0.87
     regarding
    0.80
     before
    0.80
     BEFORE
    0.78
     throughout
    0.76
     yesterday
    0.74
     concerning
    0.71
     onto
    0.70
    Act Density 0.215%

    No Known Activations