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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "two"

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ly
    -0.72
    FXML
    -0.68
    one
    -0.67
    ton
    -0.66
     one
    -0.65
    onel
    -0.64
    One
    -0.63
    per
    -0.62
    ter
    -0.61
    ger
    -0.60
    POSITIVE LOGITS
    vábbi
    0.82
    crapers
    0.81
    otka
    0.78
     CreateTagHelper
    0.77
    liminaries
    0.77
    tempted
    0.77
     kaarangay
    0.76
    aritions
    0.75
     referenties
    0.75
    nastics
    0.74
    Act Density 0.055%

    No Known Activations