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

    Neuronpedia

    INDEX
    Explanations

    phrases related to chemical burns

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    respective
    -0.67
     Helpful
    -0.59
    :[
    -0.58
    atively
    -0.58
    ,—
    -0.57
    ificant
    -0.57
    task
    -0.56
    ieth
    -0.55
    ECA
    -0.54
    iple
    -0.54
    POSITIVE LOGITS
     albeit
    0.73
    MSN
    0.68
    Magikarp
    0.67
     shattering
    0.62
     circa
    0.62
     culminating
    0.62
     although
    0.61
     which
    0.60
     eh
    0.60
     aka
    0.57
    Act Density 0.611%

    No Known Activations