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

    Neuronpedia

    INDEX
    Explanations

    phrases related to phases or stages of processes and their transitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    afort
    -0.16
    ancia
    -0.15
    ÑĢд
    -0.15
    allet
    -0.15
    eline
    -0.14
    rosse
    -0.14
    atio
    -0.14
    acid
    -0.14
    abd
    -0.14
    æŁĵ
    -0.14
    POSITIVE LOGITS
    лев
    0.16
    åī
    0.15
     manual
    0.15
     Pla
    0.15
    PGA
    0.15
     ray
    0.15
     ’
    0.14
     Morse
    0.14
     Bare
    0.14
    elon
    0.14
    Act Density 0.258%

    No Known Activations