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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to assumptions and faith in interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rome
    -0.18
    esian
    -0.17
    erman
    -0.17
    essler
    -0.16
    лав
    -0.16
    Ø©
    -0.15
    etting
    -0.15
    udas
    -0.15
    ее
    -0.15
    Assert
    -0.15
    POSITIVE LOGITS
    /assert
    0.23
    ably
    0.23
    ptions
    0.20
    PTION
    0.18
    ively
    0.17
    conds
    0.16
    nal
    0.16
     Worst
    0.15
    ptive
    0.15
     worst
    0.15
    Act Density 0.026%

    No Known Activations