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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences ending with `"."`

    oai_token-act-pair · gpt-3.5-turbo

    terminal punctuation, particularly periods and other sentence-ending markers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     starved
    -0.72
     consec
    -0.66
     wardrobe
    -0.65
     fairy
    -0.64
     thrill
    -0.63
     lifes
    -0.63
     habit
    -0.63
     uncond
    -0.62
     ninja
    -0.62
     scenery
    -0.62
    POSITIVE LOGITS
     Adds
    0.86
     Additionally
    0.84
     Towards
    0.83
     Presumably
    0.82
     Needless
    0.81
     According
    0.81
     Furthermore
    0.81
    According
    0.80
     Moreover
    0.80
     Refer
    0.79
    Act Density 0.097%

    No Known Activations