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

    Neuronpedia

    INDEX
    Explanations

    street addresses

    oai_token-act-pair · gpt-3.5-turbo

    street names and addresses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Halls
    -0.85
     Zucker
    -0.69
     advertisers
    -0.62
     Primordial
    -0.61
     Referred
    -0.58
     Candy
    -0.58
     Legions
    -0.57
    PASS
    -0.57
     praises
    -0.57
    figure
    -0.57
    POSITIVE LOGITS
    .,
    1.04
    eno
    1.01
    uid
    0.93
    ree
    0.90
    ubs
    0.86
    wn
    0.84
    vl
    0.84
    usc
    0.83
    rha
    0.81
    rs
    0.80
    Act Density 0.027%

    No Known Activations