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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a discussion or commentary on various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eo
    -0.16
    las
    -0.14
    اÙĨÛĮ
    -0.14
    ameda
    -0.14
    oretical
    -0.14
    ropri
    -0.13
    iring
    -0.13
     ê°Ģì§Ħ
    -0.13
    teri
    -0.13
    oki
    -0.13
    POSITIVE LOGITS
     how
    0.19
     behalf
    0.17
     matters
    0.16
    isse
    0.16
    slaught
    0.15
     Alg
    0.15
    ollapse
    0.15
    icken
    0.14
    rage
    0.14
    itom
    0.14
    Act Density 0.228%

    No Known Activations