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

    Neuronpedia

    INDEX
    Explanations

    phrases and terms related to description and narration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    illard
    -1.66
    ska
    -1.63
    uten
    -1.59
    HS
    -1.58
    ori
    -1.56
    ż
    -1.54
    \]\].
    -1.51
    enue
    -1.47
    )]{}
    -1.46
    \]]{}
    -1.42
    POSITIVE LOGITS
    ably
    2.32
     how
    1.73
     error
    1.51
     deprivation
    1.45
    omerase
    1.40
     atroc
    1.38
     disorder
    1.36
     them
    1.34
    quer
    1.33
     errors
    1.33
    Act Density 0.010%

    No Known Activations