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

    Neuronpedia

    INDEX
    Explanations

    terms related to stubbing or objects that are partially removed

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    neh
    -0.16
    ernel
    -0.16
     Dolphin
    -0.15
    zel
    -0.14
    ulum
    -0.14
    uda
    -0.14
    gate
    -0.14
    utenberg
    -0.14
     Tiger
    -0.14
    _UNKNOWN
    -0.13
    POSITIVE LOGITS
    isz
    0.17
    ailability
    0.16
    UGIN
    0.15
    ekim
    0.15
    omal
    0.14
    ÄĻp
    0.14
    kus
    0.14
     Ñģоп
    0.14
    ssel
    0.14
    apor
    0.14
    Act Density 0.006%

    No Known Activations