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

    Neuronpedia

    INDEX
    Explanations

    letter 'B' followed by a single digit

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter 'B' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Gutenberg
    -0.81
     Pharaoh
    -0.61
     choir
    -0.59
     Voldemort
    -0.59
     choke
    -0.59
    wcsstore
    -0.59
     dere
    -0.59
     Militia
    -0.58
     Cheong
    -0.58
     Lerner
    -0.58
    POSITIVE LOGITS
    rug
    1.13
    razen
    1.12
    odies
    1.10
    aked
    1.09
    urt
    1.08
    amboo
    1.08
    rows
    1.07
    raid
    1.05
    rief
    1.04
    anned
    1.04
    Act Density 0.059%

    No Known Activations