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

    Neuronpedia

    INDEX
    Explanations

    references to testing and experimentation processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    listdir
    -0.56
    enterOuterAlt
    -0.56
    hant
    -0.53
     Digest
    -0.53
    digest
    -0.52
    Unmount
    -0.51
    SPIRE
    -0.51
    rceil
    -0.50
    quip
    -0.50
     DialogInterface
    -0.50
    POSITIVE LOGITS
     experiment
    1.37
     Experiment
    1.34
     experiments
    1.30
     experimentation
    1.25
    experiment
    1.25
     experimented
    1.23
     experimenting
    1.23
    Experiment
    1.22
     Experiments
    1.22
    Experiments
    1.15
    Act Density 0.363%

    No Known Activations