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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "no" and its variations to indicate negation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rary
    -0.15
    nist
    -0.15
    panion
    -0.15
    noon
    -0.15
    gio
    -0.15
    ãģĦãģĨ
    -0.14
    rů
    -0.14
    419
    -0.14
    ipsis
    -0.14
    hua
    -0.14
    POSITIVE LOGITS
     matter
    0.44
     amount
    0.34
    matter
    0.31
     wonder
    0.29
     Matter
    0.28
    amount
    0.27
     sooner
    0.25
     doubt
    0.24
     Amount
    0.23
     one
    0.22
    Act Density 0.047%

    No Known Activations