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

    Neuronpedia

    INDEX
    Explanations

    Instances of names and titles related to promotions and appointments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Traceback
    -0.52
    SqlParameter
    -0.51
     MenuView
    -0.47
    kloped
    -0.47
     rela
    -0.47
    aarrggbb
    -0.46
    Alike
    -0.46
    andaan
    -0.46
    FieldNumber
    -0.46
    erals
    -0.45
    POSITIVE LOGITS
     honorary
    0.73
     Honorary
    0.68
     Designated
    0.66
     designated
    0.65
     chief
    0.64
     unofficial
    0.64
     maailman
    0.63
     hoofd
    0.63
    ########.
    0.62
     champion
    0.62
    Act Density 0.265%

    No Known Activations