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

    Neuronpedia

    INDEX
    Explanations

    references to time-related phrases

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     varandra
    -0.77
    riwal
    -0.73
     Obrador
    -0.63
    //
    -0.54
    koda
    -0.53
    tomos
    -0.52
    Geplaatst
    -0.51
    asanjo
    -0.51
     prohibido
    -0.50
    ebbe
    -0.50
    POSITIVE LOGITS
    CHREIB
    0.76
    URDAY
    0.72
    شهاد
    0.71
    udadera
    0.71
    esterday
    0.70
     BRARY
    0.68
    ntown
    0.67
     *++
    0.65
    uesday
    0.65
    terday
    0.65
    Act Density 0.022%

    No Known Activations