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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating similarity or repetition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olm
    -0.42
    RemoteException
    -0.37
    GEBURTSDATUM
    -0.37
    Diweddarwch
    -0.36
    Stam
    -0.35
    akk
    -0.35
    wra
    -0.34
    distan
    -0.33
     bion
    -0.33
     strtotime
    -0.33
    POSITIVE LOGITS
     same
    0.89
    Same
    0.79
    same
    0.78
     dieselben
    0.78
     gleichen
    0.76
     dieselbe
    0.73
     Same
    0.72
     mismas
    0.71
     selben
    0.69
     mismos
    0.69
    Act Density 0.482%

    No Known Activations