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

    Neuronpedia

    INDEX
    Explanations

    references to scientific experiments and their outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    \|_{
    -0.79
     profilo
    -0.77
     Normdatei
    -0.76
     hiér
    -0.74
    paravant
    -0.72
    Continuity
    -0.71
     rédaction
    -0.70
     htons
    -0.68
    وردار
    -0.67
    JKLM
    -0.67
    POSITIVE LOGITS
     experiment
    2.19
     experiments
    2.17
     Experiments
    1.99
     Experiment
    1.97
    Experiments
    1.84
    Experiment
    1.82
     experimental
    1.81
     EXPERIMENT
    1.80
     experimentation
    1.77
    experiment
    1.76
    Act Density 0.095%

    No Known Activations