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

    Neuronpedia

    INDEX
    Explanations

    phrases that express intention or desire

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urst
    -0.15
    trak
    -0.14
    inel
    -0.14
    ÏģαÏĤ
    -0.14
    erah
    -0.14
    reck
    -0.14
    addon
    -0.13
    ãĥ³ãĤ¸
    -0.13
    ãģ¨ãģĵãĤį
    -0.13
    âl
    -0.13
    POSITIVE LOGITS
     or
    0.20
     either
    0.17
    ckett
    0.16
     EITHER
    0.15
    ITHER
    0.15
     noun
    0.15
     soit
    0.15
    Äħd
    0.14
    either
    0.14
    ëĵł
    0.14
    Act Density 0.024%

    No Known Activations