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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "one" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     saites
    -0.77
    Havolalar
    -0.71
     Chriftian
    -0.69
     ―――――
    -0.69
    DockStyle
    -0.69
     Majefty
    -0.69
     Jefus
    -0.68
    IntoConstraints
    -0.68
     itſelf
    -0.67
     ་་
    -0.66
    POSITIVE LOGITS
     more
    0.74
     single
    0.71
     big
    0.70
     two
    0.67
     one
    0.66
     person
    0.64
     large
    0.64
     major
    0.61
     a
    0.60
     pair
    0.59
    Act Density 0.200%

    No Known Activations