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

    Neuronpedia

    INDEX
    Explanations

    references to sociological studies and frameworks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -1.35
     myſelf
    -1.30
     Efq
    -1.28
     Cæsar
    -1.26
     Jefus
    -1.21
     purpoſe
    -1.19
     Theſe
    -1.19
     himſelf
    -1.18
     themſelves
    -1.15
     ſta
    -1.14
    POSITIVE LOGITS
     per
    0.60
     in
    0.56
     di
    0.51
     que
    0.51
     im
    0.50
     Per
    0.50
     am
    0.49
     son
    0.48
     para
    0.48
     at
    0.47
    Act Density 1.330%

    No Known Activations