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

    Neuronpedia

    INDEX
    Explanations

    specific mentions or occurrences of the word "directly" in texts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "directly."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulton
    -0.78
     Peb
    -0.74
     Frame
    -0.70
     Baxter
    -0.70
    ummies
    -0.68
    ulia
    -0.65
     Scor
    -0.65
     Turtle
    -0.65
     Boys
    -0.65
     Garry
    -0.64
    POSITIVE LOGITS
     contradicted
    0.98
     benefited
    0.90
     contradicts
    0.86
     identifiable
    0.86
     contradict
    0.83
     confront
    0.80
     involved
    0.80
     addressed
    0.79
    cedented
    0.79
     implicated
    0.78
    Act Density 0.010%

    No Known Activations