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

    Neuronpedia

    INDEX
    Explanations

    phrases that express comparisons or relative distances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    as far as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⓧ
    -0.65
    -0.50
    Portály
    -0.46
    nexpected
    -0.46
    FieldBuilder
    -0.45
     builder
    -0.44
     soudain
    -0.43
    UnusedPrivate
    -0.43
    addPreferredGap
    -0.43
    FromNib
    -0.42
    POSITIVE LOGITS
    TargetException
    0.58
     Concerning
    0.54
    adalajara
    0.51
    Concerning
    0.49
     regarding
    0.49
     concerning
    0.48
    oweit
    0.48
    Regarding
    0.47
     tetrachloride
    0.47
    ]-->
    0.45
    Act Density 0.009%

    No Known Activations