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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating new beginnings or significant firsts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chw
    -0.15
    agine
    -0.15
    hol
    -0.15
    chg
    -0.15
    anh
    -0.15
    ropa
    -0.14
    endar
    -0.14
    ard
    -0.14
    /logger
    -0.14
    inand
    -0.14
    POSITIVE LOGITS
    uspend
    0.15
    iferay
    0.14
    eliac
    0.14
    że
    0.13
    enus
    0.13
    .dsl
    0.13
    _FOREACH
    0.13
    lb
    0.13
    ighton
    0.13
    183
    0.12
    Act Density 0.336%

    No Known Activations