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

    Neuronpedia

    INDEX
    Explanations

    words related to endings or conclusions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isible
    -0.19
     tslib
    -0.17
    inerary
    -0.16
    forme
    -0.16
    atables
    -0.15
    imenti
    -0.15
    ieme
    -0.15
    atform
    -0.15
    ledged
    -0.15
    á»Ļn
    -0.14
    POSITIVE LOGITS
     wind
    0.23
    ow
    0.21
     Wind
    0.20
     ended
    0.20
     up
    0.19
     wound
    0.19
     us
    0.19
    ear
    0.18
    Wind
    0.18
    wind
    0.18
    Act Density 0.011%

    No Known Activations