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

    Neuronpedia

    INDEX
    Explanations

    phrases referring to a confirmation or declaration of something

    oai_token-act-pair · gpt-3.5-turbo

    repetitions of the phrase "this is."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    luaj
    -0.66
     floats
    -0.64
    styles
    -0.63
    bies
    -0.62
     coasts
    -0.62
    chev
    -0.62
    astically
    -0.61
     cones
    -0.60
     peg
    -0.59
     stripes
    -0.59
    POSITIVE LOGITS
    rael
    0.95
     definitely
    0.93
     unlikely
    0.84
     abundantly
    0.83
     likely
    0.81
     important
    0.79
     undoubtedly
    0.79
     also
    0.78
     not
    0.78
     undeniable
    0.77
    Act Density 0.164%

    No Known Activations