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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating future actions or directions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ä¸Ī
    -0.18
    kening
    -0.17
    аÑĢÑĩ
    -0.15
    ptal
    -0.15
     اÙĦاخ
    -0.15
    .metro
    -0.14
    zim
    -0.14
    urg
    -0.14
    _MODULES
    -0.14
    оÑģÑĥд
    -0.13
    POSITIVE LOGITS
    aban
    0.17
     after
    0.16
    endo
    0.16
     desert
    0.15
    isters
    0.14
     before
    0.14
    utherland
    0.14
    406
    0.14
     Gallagher
    0.14
    at
    0.14
    Act Density 0.386%

    No Known Activations