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

    Neuronpedia

    INDEX
    Explanations

    statements that make strong assertions or criticisms regarding societal issues, particularly around immigration, violence, and community dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idum
    -0.50
     vorstellen
    -0.47
     vista
    -0.46
    loh
    -0.45
    tagHelperRunner
    -0.45
     installé
    -0.45
     installation
    -0.43
     تسم
    -0.43
    verhältnisse
    -0.42
    Collegamenti
    -0.42
    POSITIVE LOGITS
     uttered
    1.01
     utterances
    1.01
     statements
    0.89
     worded
    0.89
     words
    0.86
     utterance
    0.85
    SequentialGroup
    0.85
     uttering
    0.85
     speech
    0.79
    statements
    0.76
    Act Density 0.841%

    No Known Activations