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

    Neuronpedia

    INDEX
    Explanations

    the word "ob" followed by a number that is not equivalent to 10

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "ob" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ivities
    -0.72
    UAL
    -0.72
    Angelo
    -0.68
     Divinity
    -0.67
    ³³³³³³³³
    -0.66
     Falk
    -0.66
    ignt
    -0.64
     Uriel
    -0.64
    yards
    -0.64
    ³³³³
    -0.64
    POSITIVE LOGITS
    acter
    1.23
    edience
    1.18
    server
    1.15
    lique
    1.13
    edient
    1.12
    rien
    1.10
    fusc
    1.09
    otom
    1.08
    acco
    1.08
    ranch
    1.07
    Act Density 0.026%

    No Known Activations