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

    Neuronpedia

    INDEX
    Explanations

    phrases related to interpersonal relationships and societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    odom
    -0.16
    iou
    -0.16
     Suddenly
    -0.15
     suddenly
    -0.15
    aland
    -0.14
     slow
    -0.14
    oded
    -0.14
     sudden
    -0.14
    vr
    -0.14
    mans
    -0.14
    POSITIVE LOGITS
    instead
    0.21
     instead
    0.20
    åıªæĺ¯
    0.20
     Instead
    0.19
    å¾Ĵ
    0.19
     вмеÑģÑĤ
    0.18
     merely
    0.18
    Instead
    0.18
     worse
    0.17
    nothing
    0.16
    Act Density 0.256%

    No Known Activations