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

    Neuronpedia

    INDEX
    Explanations

    the repeated use of the word "that" in various contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     beginnetje
    -0.89
    Jeografia
    -0.74
    CloseOperation
    -0.71
    RetentionPolicy
    -0.71
    ViewFeatures
    -0.69
    jspx
    -0.68
     ModelExpression
    -0.67
    Referanser
    -0.66
    Παραπομπές
    -0.64
    illoma
    -0.63
    POSITIVE LOGITS
     tslint
    0.59
     habet
    0.49
    <?
    0.48
    __))
    0.48
    Ports
    0.47
     bestäm
    0.47
    dow
    0.47
    dor
    0.47
     parach
    0.47
    piv
    0.46
    Act Density 0.040%

    No Known Activations