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

    Neuronpedia

    INDEX
    Explanations

    terms related to financial concepts, specifically the concept of 'fixed'

    oai_token-act-pair · gpt-3.5-turbo

    references to fixed or constant values in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anasia
    -0.93
    inx
    -0.83
    esis
    -0.81
    ivals
    -0.81
    udi
    -0.77
    etic
    -0.77
    æѦ
    -0.75
    alogy
    -0.74
    ammy
    -0.73
    ONSORED
    -0.72
    POSITIVE LOGITS
     fixed
    0.91
    fixed
    0.85
     Fixed
    0.73
    ĵĺ
    0.72
     satisf
    0.69
     fix
    0.68
    lear
    0.67
    ties
    0.65
     fixing
    0.65
     beam
    0.63
    Act Density 0.011%

    No Known Activations