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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate summarization or presentation of research results and data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Decided
    -0.57
    boru
    -0.53
    principalTable
    -0.51
    DataPropertyName
    -0.46
    Viitteet
    -0.46
    hagen
    -0.45
    ΗΣ
    -0.44
    Einzelnachweise
    -0.44
    setdefault
    -0.43
    haustible
    -0.43
    POSITIVE LOGITS
     given
    1.14
     shown
    1.12
    given
    0.94
     listed
    0.93
     summarized
    0.92
     presented
    0.91
    shown
    0.85
     tabulated
    0.82
     depicted
    0.81
     summarised
    0.80
    Act Density 0.745%

    No Known Activations