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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences starting with "If there is one thing that" or similar variations

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    EA
    -0.57
    ocker
    -0.56
    ONSORED
    -0.55
     Erit
    -0.54
     provoking
    -0.54
    SEE
    -0.53
     Mecca
    -0.52
     attaching
    -0.52
    full
    -0.52
     stressing
    -0.51
    POSITIVE LOGITS
    abouts
    1.41
    upon
    1.08
     exists
    0.90
    fore
    0.85
     are
    0.76
    FORE
    0.75
    after
    0.74
    with
    0.74
    mins
    0.74
     isn
    0.74
    Act Density 0.122%

    No Known Activations