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

    Neuronpedia

    INDEX
    Explanations

    words related to medical and health issues

    oai_token-act-pair · gpt-3.5-turbo

    forms of the verb "to be" and their related conjugations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bies
    -0.65
    cation
    -0.63
    bie
    -0.62
    apper
    -0.61
    stand
    -0.61
    deb
    -0.60
    ]),
    -0.60
    ð
    -0.60
    ipher
    -0.58
    verse
    -0.58
    POSITIVE LOGITS
     also
    1.02
     therefore
    0.82
     furthermore
    0.77
     certainly
    0.77
    etsk
    0.76
     moreover
    0.72
     unclear
    0.72
    vor
    0.68
     reminded
    0.67
     ironic
    0.66
    Act Density 0.365%

    No Known Activations