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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "too" indicating excessiveness or intensity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    st
    -0.19
    pu
    -0.19
     toch
    -0.18
    map
    -0.18
    tron
    -0.17
    do
    -0.17
    ry
    -0.17
    noon
    -0.17
    post
    -0.16
    termin
    -0.16
    POSITIVE LOGITS
    led
    0.28
     boot
    0.27
    ledo
    0.24
     Boot
    0.23
    o
    0.21
    gether
    0.21
    thers
    0.20
    oot
    0.20
    oooooooo
    0.20
    oooo
    0.19
    Act Density 0.022%

    No Known Activations