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

    Neuronpedia

    INDEX
    Explanations

    phrases that denote the highest degree or severity of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ankan
    -0.07
    isine
    -0.07
     onAnimation
    -0.06
    oran
    -0.06
    ocre
    -0.06
    iid
    -0.06
    parm
    -0.06
    EGA
    -0.06
    umat
    -0.06
    _FIXED
    -0.06
    POSITIVE LOGITS
    WOOD
    0.08
    wood
    0.07
    linger
    0.07
     recent
    0.07
    бÑĥдÑĮ
    0.07
    /respond
    0.07
     latest
    0.06
    ole
    0.06
    .ptr
    0.06
    \Mapping
    0.06
    Act Density 0.035%

    No Known Activations