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

    Neuronpedia

    INDEX
    Explanations

    text indicating movement or transition from one place to another

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "there" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    box
    -0.64
    aah
    -0.63
     ACPI
    -0.60
     Ing
    -0.60
     Mant
    -0.58
     percentile
    -0.58
    buster
    -0.58
     @@
    -0.57
    HH
    -0.57
     commons
    -0.56
    POSITIVE LOGITS
     onwards
    1.09
     onward
    1.02
    ģ«
    0.82
    forth
    0.81
    uther
    0.76
     culmin
    0.73
    icter
    0.73
    llah
    0.72
    assi
    0.71
    aki
    0.71
    Act Density 0.072%

    No Known Activations