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

    Neuronpedia

    INDEX
    Explanations

    words related to explanations, predictions, protections, and preventatives

    oai_token-act-pair · gpt-3.5-turbo

    words related to explanations and preventive measures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    buck
    -0.84
    igrate
    -0.81
    uate
    -0.80
    igon
    -0.78
    cedented
    -0.78
    ruary
    -0.77
    edly
    -0.77
    puter
    -0.76
    eem
    -0.76
    ãģ®éŃĶ
    -0.75
    POSITIVE LOGITS
     measures
    0.93
     qualities
    0.87
     Measures
    0.84
     force
    0.79
     intent
    0.79
     mechanism
    0.79
     mechanisms
    0.78
     powers
    0.77
     capability
    0.76
     tendencies
    0.76
    Act Density 0.210%

    No Known Activations