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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences denoting a notable or remarkable event or situation

    oai_token-act-pair · gpt-3.5-turbo

    punctuation, particularly periods indicating the end of statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     millenn
    -0.78
     corner
    -0.66
     misunderstood
    -0.65
     aven
    -0.64
     nodd
    -0.63
     shootout
    -0.62
     creeping
    -0.62
     barg
    -0.61
     negotiated
    -0.61
     unsus
    -0.59
    POSITIVE LOGITS
    _.
    1.12
    Pa
    1.06
    -.
    1.02
     .
    0.91
    uj
    0.87
    hack
    0.84
    mobi
    0.84
    NET
    0.83
    gif
    0.81
    Ħ¢
    0.80
    Act Density 0.040%

    No Known Activations