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

    Neuronpedia

    INDEX
    Explanations

    phrases or words related to positions or opinions maintained on certain issues

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "stance" and related terms, which refer to positions or viewpoints on various issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    otin
    -0.69
    random
    -0.67
    rive
    -0.64
    Bus
    -0.64
    inders
    -0.64
    Collect
    -0.63
    apes
    -0.61
    ogg
    -0.61
    Random
    -0.61
    GV
    -0.61
    POSITIVE LOGITS
     stance
    3.65
     stances
    2.85
     posture
    1.96
     position
    1.58
     attitude
    1.43
     viewpoint
    1.28
     mindset
    1.24
     Position
    1.14
     tactic
    1.14
     positions
    1.14
    Act Density 0.016%

    No Known Activations