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

    Neuronpedia

    INDEX
    Explanations

    words related to extreme beliefs or actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "radical" and related forms in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pool
    -0.74
     Milky
    -0.72
    luck
    -0.72
    gp
    -0.71
    gio
    -0.71
     Trophy
    -0.70
    IES
    -0.70
     Hath
    -0.68
    ************
    -0.67
    mouth
    -0.67
    POSITIVE LOGITS
     radical
    3.51
    radical
    3.22
     Radical
    2.68
     radicals
    2.49
     militant
    1.69
     extremist
    1.66
     revolutionary
    1.59
     extremism
    1.46
     subversive
    1.40
     fundamentalist
    1.39
    Act Density 0.015%

    No Known Activations