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

    Neuronpedia

    INDEX
    Explanations

    phrases related to movement or transitions between locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥįãĥ«
    -0.18
    ismet
    -0.16
    OUCH
    -0.15
    andal
    -0.14
    andi
    -0.14
    caf
    -0.14
    缣
    -0.14
    ed
    -0.14
    ique
    -0.13
    ime
    -0.13
    POSITIVE LOGITS
    vertiser
    0.16
    ÐĶÐIJ
    0.15
    reater
    0.15
    áºŃt
    0.15
    undi
    0.15
    ardown
    0.14
    bidden
    0.14
    <?↵
    0.14
    ÐĶÐļ
    0.14
    raud
    0.14
    Act Density 0.112%

    No Known Activations