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

    Neuronpedia

    INDEX
    Explanations

    references to snakes and their behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    loha
    -0.15
    arton
    -0.15
    abouts
    -0.15
    assel
    -0.14
    isa
    -0.14
    áÄį
    -0.14
    etter
    -0.14
    allas
    -0.14
    rase
    -0.14
    ãĥ§
    -0.14
    POSITIVE LOGITS
     æĻ´
    0.16
    ington
    0.16
    bard
    0.15
     bush
    0.15
    ycastle
    0.14
    inish
    0.14
     ActiveSupport
    0.14
     ngoại
    0.13
    654
    0.13
    itched
    0.13
    Act Density 0.004%

    No Known Activations