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

    Neuronpedia

    INDEX
    Explanations

    phrases related to adjectives describing properties or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    determiners and adjectives indicating quantity or quality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ambassador
    -0.74
    adobe
    -0.70
     Citation
    -0.69
    most
    -0.68
     Skies
    -0.67
    pedia
    -0.63
     CLSID
    -0.63
    assi
    -0.62
     Ambassador
    -0.61
    =[
    -0.60
    POSITIVE LOGITS
    Ô
    0.78
    osher
    0.77
    abal
    0.76
    à©
    0.75
    Ò
    0.74
    WER
    0.73
    ostic
    0.72
    artment
    0.67
    ographical
    0.66
    ources
    0.65
    Act Density 0.242%

    No Known Activations