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

    Neuronpedia

    INDEX
    Explanations

    phrases related to researchers and scientists

    oai_token-act-pair · gpt-3.5-turbo

    terms related to scientists and researchers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilver
    -0.84
    eni
    -0.83
    pring
    -0.82
    ween
    -0.82
    etting
    -0.81
    ensible
    -0.79
    avers
    -0.78
    ensation
    -0.77
    ensical
    -0.76
    aver
    -0.76
    POSITIVE LOGITS
     extraord
    0.93
    ufact
    0.80
    ="#
    0.71
    ãĤ¶
    0.71
     herself
    0.70
     Pyro
    0.70
    onom
    0.69
    OAD
    0.69
    OGR
    0.68
    ically
    0.67
    Act Density 0.215%

    No Known Activations