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

    Neuronpedia

    INDEX
    Explanations

    references to pendulums and their applications or significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /***/
    -0.18
    utherford
    -0.16
    erah
    -0.16
    alnız
    -0.16
    herits
    -0.15
    éric
    -0.15
    verty
    -0.15
    oÅĪ
    -0.14
    erior
    -0.14
    gles
    -0.14
    POSITIVE LOGITS
    ulum
    0.37
    leton
    0.30
    ulous
    0.24
     pend
    0.22
    ennis
    0.22
    ragon
    0.21
     Ore
    0.19
    jabi
    0.18
    ek
    0.18
    pend
    0.18
    Act Density 0.004%

    No Known Activations