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

    Neuronpedia

    INDEX
    Explanations

    names of individuals preceded by specific terms like titles or organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to photovoltaic (PV) technology and specific individuals' names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    perature
    -0.76
    ģĸ
    -0.72
    swick
    -0.64
    hips
    -0.64
    itude
    -0.63
     Freddie
    -0.61
    achusetts
    -0.61
     dove
    -0.60
     defiance
    -0.60
    éĹĺ
    -0.59
    POSITIVE LOGITS
    ulent
    0.82
    lator
    0.78
    los
    0.78
    OK
    0.76
    assic
    0.76
     Kur
    0.75
    istani
    0.75
    gew
    0.74
    00007
    0.74
    ihara
    0.74
    Act Density 0.021%

    No Known Activations