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

    Neuronpedia

    INDEX
    Explanations

    references to experimental procedures and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     profilo
    -0.72
    \|_{
    -0.71
    VOS
    -0.69
     glutathione
    -0.64
    Continuity
    -0.64
    afone
    -0.64
    iteracy
    -0.63
    athione
    -0.62
     htons
    -0.61
    〉
    -0.61
    POSITIVE LOGITS
     experiments
    2.15
     experiment
    2.09
     Experiments
    1.99
     Experiment
    1.88
    Experiments
    1.85
     experimentation
    1.73
     EXPERIMENT
    1.72
    experiment
    1.71
     experimental
    1.71
    Experiment
    1.70
    Act Density 0.091%

    No Known Activations