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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate transformation or change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     maxHeight
    -0.15
    101
    -0.15
    ää
    -0.15
    agoon
    -0.14
     past
    -0.14
    ãĥł
    -0.14
    uktur
    -0.14
    ovid
    -0.14
    emade
    -0.14
    upal
    -0.13
    POSITIVE LOGITS
    aram
    0.16
    ÃŃd
    0.16
    áno
    0.15
    ARAM
    0.14
    EMA
    0.14
    æ±Ĥè´Ń
    0.14
    tail
    0.14
    ects
    0.13
    mos
    0.13
    ãģĵãĤį
    0.13
    Act Density 0.058%

    No Known Activations