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

    Neuronpedia

    INDEX
    Explanations

    terms that indicate favorable or unfavorable conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ivation
    -0.15
    eron
    -0.15
    igon
    -0.14
    atsu
    -0.14
    /images
    -0.14
    vette
    -0.14
     noqa
    -0.13
    owns
    -0.13
    Insn
    -0.13
    _binding
    -0.13
    POSITIVE LOGITS
    ably
    0.25
     favor
    0.18
    nable
    0.17
    entially
    0.15
    cala
    0.15
    覧
    0.15
    abler
    0.15
    bere
    0.15
    ----------------------------------------------------------------------
    0.15
    ise
    0.15
    Act Density 0.052%

    No Known Activations