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

    Neuronpedia

    INDEX
    Explanations

    phrases related to media bias and political discourse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ReusableCell
    -0.49
    bootstrapcdn
    -0.41
    URLException
    -0.38
     surla
    -0.37
     poveznice
    -0.37
    setVerticalGroup
    -0.36
    QUADS
    -0.33
    ThroughAttribute
    -0.32
    succeeded
    -0.32
     kasarigan
    -0.31
    POSITIVE LOGITS
     ignore
    2.61
     ignored
    2.47
     ignoring
    2.34
     ignores
    2.31
     Ignore
    2.27
    ignore
    2.14
    Ignore
    2.06
     Ignoring
    2.05
     Ign
    2.02
     ignor
    2.00
    Act Density 0.922%

    No Known Activations