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

    Neuronpedia

    INDEX
    Explanations

    random strings of characters

    oai_token-act-pair · gpt-3.5-turbo

    special characters or non-standard symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Vaugh
    -0.84
     misunder
    -0.80
     pedest
    -0.75
    wagen
    -0.74
    ĸļ
    -0.68
     carbohyd
    -0.66
     vulner
    -0.64
     livelihood
    -0.64
     knees
    -0.64
     fame
    -0.63
    POSITIVE LOGITS
    ï¸ı
    1.03
    VERTISEMENT
    0.79
    Minor
    0.76
    ½
    0.73
    cffffcc
    0.72
    âĪ
    0.68
    eric
    0.68
    Pol
    0.68
    °
    0.68
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    0.66
    Act Density 0.078%

    No Known Activations