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

    Neuronpedia

    INDEX
    Explanations

    phrases that express negation or contradiction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OrCreate
    -0.15
    usat
    -0.15
    .styleable
    -0.14
    branches
    -0.14
    áÄį
    -0.14
     pand
    -0.14
    ffset
    -0.14
     Md
    -0.14
     Bord
    -0.14
     branches
    -0.14
    POSITIVE LOGITS
    alach
    0.16
    unning
    0.16
    uries
    0.15
    omi
    0.15
    dob
    0.14
    Invoker
    0.14
    erval
    0.14
    ëĶ©
    0.14
    -Ta
    0.14
    obus
    0.14
    Act Density 0.004%

    No Known Activations