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

    Neuronpedia

    INDEX
    Explanations

    phrases referring to a specific subject or topic

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "this."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãģ®ç
    -0.60
    ettes
    -0.59
    rang
    -0.59
    rider
    -0.56
    jon
    -0.56
    iae
    -0.56
    lia
    -0.56
    uster
    -0.54
    ylum
    -0.53
    eker
    -0.52
    POSITIVE LOGITS
     this
    2.34
    this
    1.81
     THIS
    1.71
     these
    1.65
    these
    1.28
    THIS
    1.19
     THESE
    1.13
     tonight
    1.09
    This
    1.07
     This
    1.01
    Act Density 0.217%

    No Known Activations