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

    Neuronpedia

    INDEX
    Explanations

    words indicating changes or variations in conditions or states

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    LookAnd
    -0.56
     is
    -0.51
     مشين
    -0.51
    EndTag
    -0.51
    Aholisi
    -0.50
     also
    -0.49
    ValueStyle
    -0.48
    getDescriptor
    -0.48
     nostru
    -0.48
    Salta
    -0.47
    POSITIVE LOGITS
    CloseOperation
    0.79
    CppCodeGen
    0.67
    tuan
    0.65
    tinh
    0.63
     personal
    0.62
     Secretary
    0.61
    SPATH
    0.61
    VolleyError
    0.60
     nakalista
    0.60
    personal
    0.59
    Act Density 0.368%

    No Known Activations