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

    Neuronpedia

    INDEX
    Explanations

    references to missing or absence of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate missing something or a sense of absence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¼ãĤ¯
    -0.83
    rir
    -0.72
    Ĥİ
    -0.71
    rha
    -0.70
    owned
    -0.69
     aided
    -0.69
     agg
    -0.68
    uliffe
    -0.68
    ĪĴ
    -0.68
    itarian
    -0.67
    POSITIVE LOGITS
     altogether
    0.85
     dearly
    0.82
     spots
    0.81
    psey
    0.76
     rehearsal
    0.76
     opportunities
    0.72
     opportunity
    0.72
    ometown
    0.66
     spot
    0.66
     concerts
    0.66
    Act Density 0.125%

    No Known Activations