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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political controversies and opinions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    emi
    -0.74
    Times
    -0.71
    zar
    -0.69
    ibble
    -0.67
    shift
    -0.67
    hart
    -0.66
    busters
    -0.66
    dog
    -0.65
    agon
    -0.65
    du
    -0.65
    POSITIVE LOGITS
     furthermore
    1.37
     consequently
    1.34
     moreover
    1.26
     therefore
    1.21
     secondly
    1.16
     hence
    1.16
     thus
    1.15
     thence
    1.12
     preferably
    1.10
     optionally
    1.05
    Act Density 0.830%

    No Known Activations