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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating various viewpoints or perspectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Duffy
    -0.15
     Rosenstein
    -0.15
    up
    -0.15
    chw
    -0.15
    Ĥ
    -0.14
    ento
    -0.14
    ert
    -0.13
    lt
    -0.13
     Terminal
    -0.13
     sty
    -0.13
    POSITIVE LOGITS
    Īëĭ¤
    0.16
    ourcem
    0.16
    acho
    0.15
    arih
    0.15
    oreach
    0.15
    lington
    0.14
    ">//
    0.14
    meld
    0.14
    encodeURIComponent
    0.14
    atu
    0.14
    Act Density 0.030%

    No Known Activations