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

    Neuronpedia

    INDEX
    Explanations

    measures or values related to a numerical scale

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vw
    -0.15
    áÄį
    -0.15
     Alman
    -0.14
    åĬª
    -0.14
    orian
    -0.14
    reo
    -0.14
     Rum
    -0.13
    874
    -0.13
     FOREIGN
    -0.13
    lemen
    -0.13
    POSITIVE LOGITS
    ronic
    0.15
    ataka
    0.15
    blr
    0.14
    ailability
    0.14
    soever
    0.14
    arih
    0.14
    Unsafe
    0.14
    imest
    0.14
    sink
    0.14
    ensis
    0.14
    Act Density 0.009%

    No Known Activations