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

    Neuronpedia

    INDEX
    Explanations

    pronouns or determiners used with verbs indicating taking or bringing something along with someone

    oai_token-act-pair · gpt-3.5-turbo

    references to companionship and relationships involving the pronoun "me", "us", "him", or "you"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ´ãĤ¡
    -0.73
    ãĥĩãĤ£
    -0.64
     probabilities
    -0.63
     parity
    -0.61
     imbalance
    -0.58
     significance
    -0.58
    76561
    -0.58
     irony
    -0.57
    ggles
    -0.57
    NP
    -0.57
    POSITIVE LOGITS
     wherever
    0.95
     onstage
    0.85
     everywhere
    0.79
    stal
    0.78
     whenever
    0.77
    à¼
    0.74
    hani
    0.73
     touring
    0.72
     throughout
    0.70
     downstairs
    0.67
    Act Density 0.182%

    No Known Activations