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

    Neuronpedia

    INDEX
    Explanations

    numeric values and patterns, particularly those associated with parameters or metrics in a structured format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Nine
    -0.71
     Nine
    -0.69
     nineteen
    -0.69
     twelve
    -0.66
     eighteen
    -0.66
     nine
    -0.65
     Six
    -0.65
     sixteen
    -0.65
    Six
    -0.64
     eleven
    -0.64
    POSITIVE LOGITS
    7
    0.89
     nahilalakip
    0.63
    AddTagHelper
    0.62
     Effectiveness
    0.62
     Effective
    0.61
    таратура
    0.60
     INVENTION
    0.59
     Tinto
    0.59
    achite
    0.59
    inawa
    0.58
    Act Density 0.325%

    No Known Activations