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

    Neuronpedia

    INDEX
    Explanations

    determiners or pronouns followed by verbs in past participle form

    oai_token-act-pair · gpt-3.5-turbo

    references to quantities and costs in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nowhere
    -0.74
    =/
    -0.73
    ometime
    -0.68
    mony
    -0.65
     placement
    -0.63
    character
    -0.62
     backdrop
    -0.61
    found
    -0.60
    reenshot
    -0.60
     Laun
    -0.59
    POSITIVE LOGITS
     affected
    0.88
     impacted
    0.83
     Affect
    0.78
     sway
    0.75
    Damage
    0.74
     influenced
    0.74
     affect
    0.73
     depends
    0.72
     depend
    0.70
     affects
    0.69
    Act Density 0.133%

    No Known Activations