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

    Neuronpedia

    INDEX
    Explanations

    mentions of the name "Alton" with varying activations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the suffix "ton."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    FACE
    -0.75
    PER
    -0.73
    iliate
    -0.71
    stract
    -0.71
    BILITIES
    -0.69
    代
    -0.69
    Tx
    -0.69
    ptive
    -0.69
    saf
    -0.69
    Magikarp
    -0.67
    POSITIVE LOGITS
    neau
    0.95
    icum
    0.93
    nian
    0.91
    nel
    0.85
    ews
    0.83
    nia
    0.82
    ©¶æ¥µ
    0.80
    ality
    0.76
    ians
    0.76
    osaurus
    0.76
    Act Density 0.039%

    No Known Activations