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

    Neuronpedia

    INDEX
    Explanations

    phrases that end with a specific symbol or character

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of a specific non-standard character or symbol

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ropes
    -0.79
     levers
    -0.72
     tides
    -0.72
     vulner
    -0.72
     incorpor
    -0.71
     apes
    -0.70
     surv
    -0.69
     machines
    -0.68
     grips
    -0.68
     pleasures
    -0.67
    POSITIVE LOGITS
    ï¸ı
    1.22
    âĶĢâĶĢ
    1.18
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    0.93
    STER
    0.85
     Advertisement
    0.77
    âĹ
    0.76
    °
    0.76
    \-
    0.75
     Edited
    0.75
    )</
    0.75
    Act Density 0.121%

    No Known Activations