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

    Neuronpedia

    INDEX
    Explanations

    suggestions for experimentation and testing different options

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     protéger
    -0.54
     getLayout
    -0.53
    SPIRE
    -0.52
    forcement
    -0.52
     sahiptir
    -0.51
    بوابة
    -0.49
     WARRANTIES
    -0.49
     waking
    -0.48
     sää
    -0.48
     Gato
    -0.47
    POSITIVE LOGITS
     experiment
    1.21
     Experiment
    1.17
     experimentation
    1.11
     experiments
    1.11
    experiment
    1.09
     Experiments
    1.05
    Experiment
    1.04
     experimente
    1.04
     EXPERIMENT
    1.04
     experimented
    1.02
    Act Density 0.168%

    No Known Activations