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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating supporting or opposing an argument

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of a specific symbol or character

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Buyable
    -0.65
    çIJ
    -0.65
     GPS
    -0.65
     Circus
    -0.65
     Samoa
    -0.63
    íķ
    -0.63
     tsunami
    -0.63
     Leilan
    -0.62
     counselling
    -0.61
     shack
    -0.60
    POSITIVE LOGITS
    should
    1.01
    £
    0.92
    shall
    0.91
    ould
    0.89
    said
    0.88
    might
    0.86
    could
    0.86
    Ĵ
    0.85
    sure
    0.85
    must
    0.83
    Act Density 0.287%

    No Known Activations