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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal experiences or opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     purpoſe
    -0.83
    ſelves
    -0.79
     صوتيه
    -0.76
    Hentet
    -0.76
     Normdatei
    -0.75
    ſelf
    -0.72
    AndEndTag
    -0.72
    expandindo
    -0.72
     الحره
    -0.71
     myſelf
    -0.71
    POSITIVE LOGITS
     saying
    0.98
     said
    0.85
     says
    0.76
     sayin
    0.76
     told
    0.70
     telling
    0.70
     decimos
    0.70
     Said
    0.69
     Says
    0.68
     "
    0.67
    Act Density 0.139%

    No Known Activations