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

    Neuronpedia

    INDEX
    Explanations

    mentions of the name "Les" in the text

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Les."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ICE
    -0.73
    ARK
    -0.68
    ACTED
    -0.68
    DERR
    -0.66
    razil
    -0.64
    tops
    -0.64
    OWS
    -0.63
    YING
    -0.63
    Loading
    -0.61
    ODUCT
    -0.60
    POSITIVE LOGITS
    bians
    1.16
    bian
    1.01
    ongh
    0.81
    alog
    0.81
    nar
    0.80
    agues
    0.78
    wana
    0.75
    lie
    0.75
    oci
    0.74
    pins
    0.74
    Act Density 0.018%

    No Known Activations