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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "cannot" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     never
    -0.15
     not
    -0.15
    ano
    -0.15
    hone
    -0.14
    uting
    -0.14
    çķ
    -0.14
    never
    -0.14
    ÑĤим
    -0.14
    ropri
    -0.14
    entarios
    -0.14
    POSITIVE LOGITS
    ches
    0.20
    epad
    0.20
     necessarily
    0.19
     anymore
    0.18
    ched
    0.16
    urtle
    0.15
    eworthy
    0.15
    PAL
    0.15
    tingham
    0.14
    ervation
    0.14
    Act Density 0.016%

    No Known Activations