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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating persistence or reminders

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gest
    -0.17
    SRC
    -0.16
     IG
    -0.15
     synchron
    -0.14
    _nl
    -0.14
    ayer
    -0.14
    bor
    -0.14
    pch
    -0.14
     bob
    -0.13
    ÑĢина
    -0.13
    POSITIVE LOGITS
    -scroll
    0.15
    remen
    0.15
    dale
    0.14
    _scal
    0.14
     remember
    0.14
     reading
    0.13
    thy
    0.13
    anes
    0.13
    ollect
    0.13
    ÑĨеп
    0.13
    Act Density 0.025%

    No Known Activations