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

    Neuronpedia

    INDEX
    Explanations

    phrases related to controversial or extreme actions or beliefs

    oai_token-act-pair · gpt-3.5-turbo

    terms related to violence or violence-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asions
    -0.57
    umption
    -0.56
    itars
    -0.55
    cies
    -0.54
    istries
    -0.51
    ancies
    -0.51
    ispers
    -0.50
     interviews
    -0.49
     Scenes
    -0.49
    arton
    -0.48
    POSITIVE LOGITS
     conduit
    0.64
     starter
    0.63
     contender
    0.62
     underdog
    0.62
     worthy
    0.60
     sleeper
    0.58
     unto
    0.57
    acea
    0.56
     incarn
    0.56
     fodder
    0.56
    Act Density 0.934%

    No Known Activations