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

    Neuronpedia

    INDEX
    Explanations

    the word "mostly" in various forms and contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    LEncoder
    -0.91
    HandlerContext
    -0.71
     становника
    -0.69
    createServer
    -0.64
    ImageContext
    -0.63
    UnitTesting
    -0.62
    gements
    -0.61
    Delimited
    -0.60
    atguigu
    -0.59
     StringTokenizer
    -0.59
    POSITIVE LOGITS
     Mostly
    0.89
     assorted
    0.82
     Assorted
    0.79
    Mostly
    0.79
    ][:
    0.75
    mostly
    0.74
     mostly
    0.73
    paravant
    0.73
    Tikang
    0.69
     masak
    0.68
    Act Density 0.005%

    No Known Activations