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

    Neuronpedia

    INDEX
    Explanations

    instances of negation or exclusion in data or programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    FRING
    -0.16
    oho
    -0.15
    andle
    -0.15
    ategory
    -0.15
    unar
    -0.15
    OUCH
    -0.14
    _Tick
    -0.14
    antu
    -0.14
    SSF
    -0.14
    asan
    -0.14
    POSITIVE LOGITS
    889
    0.15
    M
    0.14
    访
    0.14
    oli
    0.14
    uch
    0.14
    546
    0.14
    avis
    0.14
    885
    0.14
    achu
    0.14
     entrev
    0.14
    Act Density 0.283%

    No Known Activations