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

    Neuronpedia

    INDEX
    Explanations

    phrases starting with 'as' and containing certain words related to chaotic situations

    oai_token-act-pair · gpt-3.5-turbo

    the presence of possessive forms or possessive constructs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Niet
    -0.66
     remed
    -0.65
     synerg
    -0.65
     Mous
    -0.64
     harmon
    -0.64
     handshake
    -0.64
     RIS
    -0.63
     warp
    -0.63
     dispers
    -0.63
     fortun
    -0.61
    POSITIVE LOGITS
    ¬
    1.28
    ı
    1.27
    ¡
    1.25
    Ī
    1.19
    ª
    1.16
    ¹
    1.14
    ķ
    1.13
    ħ
    1.11
    Ĵ
    1.11
    į
    1.10
    Act Density 0.241%

    No Known Activations