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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "letter" and phrases related to written communication

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    licet
    -0.64
    abcdefghijklmnop
    -0.60
    isalpha
    -0.58
     fidanz
    -0.57
    labelControl
    -0.56
    amını
    -0.56
    ädie
    -0.56
    ginfo
    -0.56
    glog
    -0.56
     setText
    -0.54
    POSITIVE LOGITS
    WebVitals
    0.73
    WriteTagHelper
    0.70
    hyrchwyd
    0.59
     bows
    0.57
    FieldBuilder
    0.57
    AndEndTag
    0.56
     Савезне
    0.56
     auctor
    0.55
    initComponents
    0.53
    featureID
    0.53
    Act Density 0.006%

    No Known Activations