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

    Neuronpedia

    INDEX
    Explanations

    negative statements about a situation or a claim

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize negation or contrast

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    luaj
    -0.75
    named
    -0.69
     Named
    -0.60
    ukong
    -0.59
    regate
    -0.59
     maiden
    -0.58
    ierce
    -0.58
     Repair
    -0.56
    miah
    -0.56
    isively
    -0.55
    POSITIVE LOGITS
     irrelevant
    0.87
     nowhere
    0.75
     nonetheless
    0.74
     untrue
    0.73
     hardly
    0.70
     unlikely
    0.69
     unavoidable
    0.69
     alright
    0.67
     nevertheless
    0.67
     outwe
    0.66
    Act Density 0.151%

    No Known Activations