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

    Neuronpedia

    INDEX
    Explanations

    numerical data, particularly related to measurements and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     first
    -1.08
    first
    -0.76
    Firstly
    -0.72
     Firstly
    -0.70
     firstly
    -0.69
     First
    -0.68
     erstmal
    -0.65
     FIRST
    -0.65
    First
    -0.63
    首先
    -0.60
    POSITIVE LOGITS
    ;
    0.77
     الرياضيه
    0.71
     généraux
    0.69
     récents
    0.66
     pauvres
    0.62
     ;
    0.60
    хьтан
    0.60
     autrement
    0.59
    évaluateur
    0.59
     незавершена
    0.58
    Act Density 1.721%

    No Known Activations