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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate instructions or steps related to achieving a goal

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iment
    -0.18
    lez
    -0.15
    æŀ¶
    -0.14
    guard
    -0.14
    verage
    -0.14
    vers
    -0.14
    ngth
    -0.14
    vise
    -0.14
    hower
    -0.14
    abor
    -0.14
    POSITIVE LOGITS
    omanip
    0.17
     Pend
    0.15
    681
    0.15
    769
    0.15
    igs
    0.14
    anos
    0.14
     âĪĢ
    0.14
    ffa
    0.13
    s
    0.13
    Sm
    0.13
    Act Density 0.017%

    No Known Activations