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

    Neuronpedia

    INDEX
    Explanations

    authors and researchers mentioned in academic references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imson
    -0.17
    apon
    -0.15
    ãĥĸãĥª
    -0.14
    NotAllowed
    -0.14
    μαÏĦο
    -0.14
    omin
    -0.14
    miss
    -0.14
    ãĢģãĢĬ
    -0.14
    usan
    -0.13
    egade
    -0.13
    POSITIVE LOGITS
    uzzi
    0.14
    specs
    0.13
     Flesh
    0.13
    ovich
    0.12
    .URI
    0.12
    Rew
    0.12
     cdecl
    0.12
    íķĦ
    0.12
     corres
    0.12
     snaps
    0.12
    Act Density 0.119%

    No Known Activations