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

    Neuronpedia

    INDEX
    Explanations

    special characters and symbols

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the character "âĢ" and its variations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     scattering
    -0.81
     Niet
    -0.72
     buggy
    -0.68
     princ
    -0.66
     straw
    -0.66
     answ
    -0.64
     semblance
    -0.63
     scatter
    -0.63
     bounce
    -0.62
     monop
    -0.61
    POSITIVE LOGITS
    ĸļ
    0.91
    º
    0.89
    £
    0.88
    bryce
    0.83
    ¬
    0.83
    catentry
    0.82
    §
    0.82
    ¸
    0.79
    ¾
    0.77
    Ĵ
    0.76
    Act Density 0.351%

    No Known Activations