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

    Neuronpedia

    INDEX
    Explanations

    positive and negative qualitative descriptors related to experiences or evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dabei
    -0.48
     for
    -0.41
    The
    -0.40
    on
    -0.39
    as
    -0.39
    for
    -0.39
     as
    -0.39
     recherchez
    -0.38
     anywhere
    -0.38
    in
    -0.38
    POSITIVE LOGITS
     مرئيه
    0.89
     queſta
    0.87
    niſſe
    0.84
     estekak
    0.77
     esternos
    0.76
    ſſung
    0.75
    ſicht
    0.74
    iſen
    0.74
    OGND
    0.74
    Становништво
    0.72
    Act Density 0.024%

    No Known Activations