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

    Neuronpedia

    INDEX
    Explanations

    terms related to tariffs and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stra
    -0.19
    ene
    -0.18
    ias
    -0.17
    sert
    -0.16
    elho
    -0.16
    EXPR
    -0.15
     Phelps
    -0.15
    mg
    -0.15
    gen
    -0.15
    ToFront
    -0.15
    POSITIVE LOGITS
     Tar
    0.27
    Tar
    0.24
     tar
    0.23
    iffs
    0.22
    leton
    0.19
    zan
    0.19
    onga
    0.18
    antino
    0.17
    زاÙĨ
    0.17
    tar
    0.17
    Act Density 0.008%

    No Known Activations