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

    Neuronpedia

    INDEX
    Explanations

    terms related to machine learning and machine-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    endsection
    -0.98
    PendingIntent
    -0.96
    Portail
    -0.94
     feroit
    -0.93
     larmes
    -0.91
     polaire
    -0.90
     Romains
    -0.85
     avoient
    -0.83
     rosé
    -0.82
    lamos
    -0.80
    POSITIVE LOGITS
     machines
    1.69
    Machines
    1.55
    machines
    1.52
     Machines
    1.51
     machine
    1.48
     Machine
    1.39
    machine
    1.31
     MACHINE
    1.26
    Machine
    1.24
    MACHINE
    1.22
    Act Density 0.070%

    No Known Activations