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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the removal or reduction of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the removal or loss of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ipel
    -0.80
    FK
    -0.72
    enegger
    -0.72
    gae
    -0.69
    nis
    -0.68
     Frie
    -0.67
    iard
    -0.66
     Trance
    -0.65
    izarre
    -0.65
    ouf
    -0.63
    POSITIVE LOGITS
     cart
    0.82
     away
    0.73
     Territories
    0.72
     liberty
    0.67
     responsibility
    0.65
    Redd
    0.61
     freedoms
    0.60
    rox
    0.60
     valuable
    0.60
    ł
    0.59
    Act Density 0.022%

    No Known Activations