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

    Neuronpedia

    INDEX
    Explanations

    references to multiple languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ixel
    -0.18
    oxy
    -0.16
    ourd
    -0.15
    elf
    -0.15
    etre
    -0.14
    eward
    -0.14
    .kr
    -0.14
    interest
    -0.14
    opes
    -0.13
    .ml
    -0.13
    POSITIVE LOGITS
    -speaking
    0.15
    .Unmarshal
    0.14
    Minor
    0.14
    .synthetic
    0.14
     Hao
    0.14
    .sponge
    0.14
     Minority
    0.14
    ãĥ¼ãĥª
    0.14
     plural
    0.14
     Bullet
    0.14
    Act Density 0.034%

    No Known Activations