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

    Neuronpedia

    INDEX
    Explanations

    phrases in a non-English language with special characters and diacritics

    oai_token-act-pair · gpt-3.5-turbo

    unique or special characters and symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    raints
    -1.01
     manif
    -0.90
     accur
    -0.82
    ngth
    -0.82
     misunder
    -0.77
     Instr
    -0.76
     womb
    -0.76
     tentacles
    -0.75
     horizont
    -0.75
     condem
    -0.75
    POSITIVE LOGITS
    âĶĢâĶĢ
    1.01
    à©
    0.94
    ishable
    0.93
    ĺ
    0.92
    ľ
    0.91
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    0.90
    ãĥ¼ãĥ
    0.89
    Ķ
    0.89
    ¤
    0.89
    ļ
    0.86
    Act Density 0.018%

    No Known Activations