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

    Neuronpedia

    INDEX
    Explanations

    statements about the existence or absence of conditions and restrictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    URA
    -0.16
    ÐĬ
    -0.16
    lemn
    -0.15
    _CB
    -0.15
    634
    -0.15
     Thema
    -0.15
    izik
    -0.15
    RIES
    -0.14
    ura
    -0.14
    avit
    -0.14
    POSITIVE LOGITS
     neither
    0.21
     Neither
    0.17
    plus
    0.16
    ored
    0.16
    anne
    0.16
    æ²¢
    0.15
    ansi
    0.15
    imer
    0.15
    Neither
    0.14
     no
    0.14
    Act Density 0.062%

    No Known Activations