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

    Neuronpedia

    INDEX
    Explanations

    statements expressing gratitude or appreciation

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ensical
    -0.41
    ħĭ
    -0.40
     awa
    -0.40
    ©¶æ
    -0.39
    inctions
    -0.37
    ģ«
    -0.34
     coffin
    -0.34
     vortex
    -0.33
     Cooldown
    -0.33
    psey
    -0.33
    POSITIVE LOGITS
    cause
    0.58
    then
    0.46
    said
    0.44
    whose
    0.42
    especially
    0.42
    clud
    0.42
    thus
    0.41
    nor
    0.41
    yet
    0.41
    today
    0.41
    Act Density 11.383%

    No Known Activations