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

    Neuronpedia

    INDEX
    Explanations

    phrases that contain a mix of nouns and verbs in a sentence

    oai_token-act-pair · gpt-3.5-turbo

    punctuations and commas in a list format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     incent
    -0.57
    sylv
    -0.55
     entire
    -0.53
     nodd
    -0.53
    pport
    -0.51
     footing
    -0.50
     baseline
    -0.49
    verage
    -0.48
     aggregation
    -0.48
     generators
    -0.48
    POSITIVE LOGITS
    zbollah
    0.62
     YPG
    0.56
     RTX
    0.55
    Psy
    0.54
     Photographer
    0.53
     Gentleman
    0.52
     Psy
    0.52
     Leader
    0.52
     ..........
    0.51
     Lod
    0.51
    Act Density 0.345%

    No Known Activations