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

    Neuronpedia

    INDEX
    Explanations

    terms related to publications or academic references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antry
    -0.15
    .unbind
    -0.15
    antha
    -0.14
    ucht
    -0.14
    _attached
    -0.14
    unicorn
    -0.14
     Kirk
    -0.14
    ano
    -0.13
    umer
    -0.13
     é¹
    -0.13
    POSITIVE LOGITS
     LOCK
    0.34
     Lock
    0.31
    LOCK
    0.31
     lock
    0.28
    Lock
    0.27
     Au
    0.27
     locks
    0.25
    .lock
    0.25
    Au
    0.25
     Locke
    0.24
    Act Density 0.000%

    No Known Activations