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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "no."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CREMENT
    -0.18
    uga
    -0.17
     Anything
    -0.16
    _PHP
    -0.16
    anything
    -0.16
    _resolver
    -0.15
    ÑĤин
    -0.15
    _unlock
    -0.15
    ru
    -0.14
    Anything
    -0.14
    POSITIVE LOGITS
     matter
    0.53
    matter
    0.45
     Matter
    0.42
     less
    0.25
     matters
    0.24
     mattered
    0.23
     differently
    0.23
     least
    0.23
    etically
    0.23
    lessly
    0.22
    Act Density 0.024%

    No Known Activations