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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to integration and implementation processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    crap
    -0.15
     Flake
    -0.15
    erti
    -0.15
    loff
    -0.14
    glomer
    -0.14
    UDGE
    -0.14
    ripper
    -0.14
    .experimental
    -0.14
    azi
    -0.14
    imi
    -0.14
    POSITIVE LOGITS
     into
    0.20
    Into
    0.20
     thêm
    0.20
    into
    0.19
    _into
    0.19
    ilyn
    0.18
     extra
    0.17
     Into
    0.17
     onto
    0.16
     additional
    0.16
    Act Density 0.212%

    No Known Activations