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

    Neuronpedia

    INDEX
    Explanations

    pronouns followed by words related to actions or events

    oai_token-act-pair · gpt-3.5-turbo

    the pronoun "we" and first-person expressions of collective experiences or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Leader
    -0.74
     Flavoring
    -0.72
    -+
    -0.67
     Saving
    -0.66
    ONSORED
    -0.63
     Jurassic
    -0.62
     Oral
    -0.62
     Responsibility
    -0.62
    odor
    -0.61
     Lever
    -0.61
    POSITIVE LOGITS
    'll
    1.14
    've
    1.08
    'd
    1.03
    're
    0.97
    sych
    0.94
     forg
    0.92
     encount
    0.89
     learnt
    0.84
    eks
    0.82
    alian
    0.81
    Act Density 0.261%

    No Known Activations