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

    Neuronpedia

    INDEX
    Explanations

    phrases related to computer and technology terms

    oai_token-act-pair · gpt-3.5-turbo

    instances of the letter 's'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dress
    -0.68
    orget
    -0.64
    docker
    -0.63
    mass
    -0.61
    EStream
    -0.59
    leans
    -0.58
    rolling
    -0.57
     Rothschild
    -0.57
     saline
    -0.57
    cake
    -0.56
    POSITIVE LOGITS
    ELF
    0.95
    pecially
    0.93
    ullivan
    0.89
     newest
    0.87
    selves
    0.82
    ources
    0.80
     own
    0.78
    udden
    0.73
     flagship
    0.73
    wered
    0.72
    Act Density 0.239%

    No Known Activations