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

    Neuronpedia

    INDEX
    Explanations

    references to political figures and their associated actions or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÑĨеп
    -0.17
    .updateDynamic
    -0.16
     ört
    -0.16
    ammo
    -0.15
    enci
    -0.14
    jk
    -0.14
    ahun
    -0.14
    ephir
    -0.14
    ForRow
    -0.14
    ãĥ§
    -0.14
    POSITIVE LOGITS
     former
    0.60
     Former
    0.54
    former
    0.49
    Former
    0.49
     retired
    0.37
     býval
    0.33
     erst
    0.30
     formerly
    0.29
     سابÙĤ
    0.28
     ex
    0.27
    Act Density 0.148%

    No Known Activations