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

    Neuronpedia

    INDEX
    Explanations

    phrases related to evidence and proof

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     wikipagina
    -0.72
    /></
    -0.68
    dymyr
    -0.65
    mektedir
    -0.63
    клопе
    -0.61
    SequentialGroup
    -0.60
    Xna
    -0.60
    ')}}"
    -0.59
    URLException
    -0.56
     tör
    -0.55
    POSITIVE LOGITS
     complacent
    0.77
     clueless
    0.72
     complacency
    0.71
    rrggbb
    0.70
     overkill
    0.70
     brainstorming
    0.69
     stumped
    0.66
     realism
    0.63
     shenanigans
    0.63
     considérons
    0.59
    Act Density 0.581%

    No Known Activations