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

    Neuronpedia

    INDEX
    Explanations

    ingredients used in cooking and brewing processes

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the suffix 'ces' in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uliffe
    -0.67
    asha
    -0.66
    OST
    -0.65
     neutrality
    -0.63
     laundering
    -0.61
     attribution
    -0.60
    ethical
    -0.59
     attribut
    -0.58
     contrace
    -0.58
    ¥ŀ
    -0.57
    POSITIVE LOGITS
    ces
    0.96
    creen
    0.91
    vous
    0.91
    ippi
    0.82
    uits
    0.80
    avier
    0.78
    cript
    0.77
    pan
    0.77
     Vide
    0.76
     Tyrann
    0.75
    Act Density 0.009%

    No Known Activations