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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating direction or location

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lyn
    -0.17
    uchi
    -0.16
    uct
    -0.15
    alsa
    -0.15
    antas
    -0.15
    uration
    -0.14
    olas
    -0.14
    eln
    -0.14
     Ki
    -0.14
    loo
    -0.14
    POSITIVE LOGITS
    anh
    0.20
    IFY
    0.15
    ÑĢÑĥг
    0.14
    _Construct
    0.14
    UU
    0.14
    ROUGH
    0.13
    tower
    0.13
    ãģ®ãģłãĤįãģĨ
    0.13
     ".";↵
    0.13
     esper
    0.13
    Act Density 0.022%

    No Known Activations