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

    Neuronpedia

    INDEX
    Explanations

    instances of the verb "pour" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    archiviato
    -0.73
    .*")]
    -0.70
    rahmen
    -0.65
     ziua
    -0.65
    LikeLike
    -0.64
     Merz
    -0.63
    çalves
    -0.63
    Stevens
    -0.63
    almaz
    -0.62
    paravant
    -0.62
    POSITIVE LOGITS
     pour
    2.50
    Pour
    2.34
    pour
    2.33
     Pour
    2.29
     pours
    2.21
     poured
    2.15
     POUR
    2.03
     pouring
    1.86
    POUR
    1.69
    pouring
    1.48
    Act Density 0.044%

    No Known Activations