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

    Neuronpedia

    INDEX
    Explanations

    Although statements indicating contrast or exceptions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Although."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bas
    -0.69
    tnc
    -0.69
     srfAttach
    -0.67
    Jew
    -0.64
     Jew
    -0.62
    itto
    -0.60
    rium
    -0.60
    ×ķ
    -0.59
    oiler
    -0.59
     contrace
    -0.58
    POSITIVE LOGITS
     acknowledging
    0.97
     technically
    0.92
    ts
    0.85
     conced
    0.82
     initially
    0.76
     admittedly
    0.76
     browsing
    0.69
    lihood
    0.68
     agreeing
    0.67
     downloading
    0.65
    Act Density 0.044%

    No Known Activations