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

    Neuronpedia

    INDEX
    Explanations

    phrases related to measurements and descriptors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adamente
    -0.17
     saw
    -0.17
     tore
    -0.15
    ánÃŃm
    -0.14
    050
    -0.13
    anda
    -0.13
    andan
    -0.13
    oppel
    -0.13
    segue
    -0.13
     financ
    -0.13
    POSITIVE LOGITS
    owany
    0.31
    ted
    0.29
    ized
    0.29
    ified
    0.29
    izado
    0.27
    ised
    0.27
    ificado
    0.26
    izzato
    0.26
    inated
    0.25
    ed
    0.24
    Act Density 0.079%

    No Known Activations