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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating quantity or frequency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zig
    -0.17
    aters
    -0.15
    fragistics
    -0.15
    urb
    -0.15
    forth
    -0.14
    oretical
    -0.14
    inki
    -0.14
    repid
    -0.14
    .twimg
    -0.14
    ux
    -0.14
    POSITIVE LOGITS
    -the
    0.31
    s
    0.28
     town
    0.26
    abouts
    0.25
    /about
    0.25
    town
    0.25
    about
    0.23
    -town
    0.22
    thew
    0.22
    /on
    0.21
    Act Density 0.055%

    No Known Activations