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

    Neuronpedia

    INDEX
    Explanations

    structures indicating the presence of multiple elements or considerations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     craft
    -0.16
    udu
    -0.15
    ScreenState
    -0.15
     >č↵
    -0.15
    lund
    -0.15
    amburger
    -0.15
    ÑĸÑģ
    -0.15
    ima
    -0.14
    AGMA
    -0.14
    Craft
    -0.14
    POSITIVE LOGITS
    uf
    0.15
    ghan
    0.15
    ungen
    0.15
    кÑĢаÑĹ
    0.14
    ogh
    0.14
    angling
    0.13
     belang
    0.13
    för
    0.13
    pus
    0.13
    ories
    0.13
    Act Density 0.063%

    No Known Activations