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

    Neuronpedia

    INDEX
    Explanations

    references to authors and collaborators in scientific works

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Monfieur
    -0.92
     itſelf
    -0.92
     myſelf
    -0.87
     Jefus
    -0.80
     iſt
    -0.78
     Efq
    -0.75
     houſe
    -0.72
    ſelf
    -0.72
     themſelves
    -0.72
     himſelf
    -0.71
    POSITIVE LOGITS
     HAZARD
    0.58
     hal
    0.51
    ɣ
    0.50
    yonel
    0.50
     parada
    0.50
     Hickman
    0.49
     ombro
    0.48
    qtype
    0.48
     costes
    0.47
     pemain
    0.45
    Act Density 0.225%

    No Known Activations