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

    Neuronpedia

    INDEX
    Explanations

    action-oriented words related to progression and change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oppel
    -0.15
    олÑĮно
    -0.15
    rador
    -0.14
    issor
    -0.14
    /ne
    -0.14
    еÑĢÑĤа
    -0.14
    bol
    -0.14
     backward
    -0.13
    ucks
    -0.13
    á»Ŀ
    -0.13
    POSITIVE LOGITS
    atic
    0.16
    bracht
    0.15
    ularity
    0.15
    ese
    0.15
    DDS
    0.15
    ew
    0.14
     toward
    0.14
    584
    0.14
    illas
    0.14
    orge
    0.14
    Act Density 0.049%

    No Known Activations