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

    Neuronpedia

    INDEX
    Explanations

    expressions of stress and expectations around social behavior and interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imson
    -0.16
    UCE
    -0.15
    ignon
    -0.15
    ondon
    -0.15
    estre
    -0.14
    vale
    -0.14
    redo
    -0.14
    ore
    -0.14
    åĬ
    -0.14
    ipher
    -0.14
    POSITIVE LOGITS
     dök
    0.17
    ìľĦìĽIJ
    0.16
    Std
    0.14
     Amerik
    0.14
     Meteor
    0.13
    iales
    0.13
     tuyá»ĩt
    0.13
    inke
    0.13
    duck
    0.13
    yl
    0.13
    Act Density 0.264%

    No Known Activations