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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "pose" or its variations, particularly in contexts involving photos or appearances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    spath
    -0.16
    zeug
    -0.16
    lä
    -0.15
    lej
    -0.15
    tre
    -0.14
    odge
    -0.14
    iego
    -0.14
    ');?>"
    -0.14
    lea
    -0.14
    uir
    -0.13
    POSITIVE LOGITS
    pose
    0.27
    idon
    0.26
     pose
    0.20
     Pos
    0.20
    =pos
    0.20
     Pose
    0.19
     threat
    0.18
    posed
    0.18
     poses
    0.18
    poses
    0.18
    Act Density 0.014%

    No Known Activations