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

    Neuronpedia

    INDEX
    Explanations

    expressions likely related to emotional and conversational content, such as exclamations, wondering, gasping, sighing, replying, and asking questions

    oai_token-act-pair · gpt-3.5-turbo

    special characters or unusual symbols in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     confir
    -1.08
    osponsors
    -0.88
    mercial
    -0.88
    ividual
    -0.83
    espie
    -0.79
    ilater
    -0.75
     targeted
    -0.74
    enegger
    -0.74
     latest
    -0.73
     commercially
    -0.72
    POSITIVE LOGITS
    ¹
    1.12
    ł
    1.01
    laugh
    0.91
    ¶ħ
    0.90
    ij
    0.87
    ¡
    0.87
    ¤
    0.85
    £
    0.84
    Damn
    0.84
    ĵ
    0.84
    Act Density 0.270%

    No Known Activations