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

    Neuronpedia

    INDEX
    Explanations

    names containing the substring "ton"

    oai_token-act-pair · gpt-3.5-turbo

    the keyword "ton" and its variants in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ptive
    -0.75
    PER
    -0.75
    ulative
    -0.73
    saf
    -0.71
    pling
    -0.67
     forgiveness
    -0.66
    ptions
    -0.66
    Magikarp
    -0.65
    stract
    -0.65
    BILITIES
    -0.65
    POSITIVE LOGITS
    nel
    1.12
    neau
    0.97
    nia
    0.88
    nian
    0.84
    nen
    0.83
    ews
    0.83
    ©¶æ¥µ
    0.82
    ville
    0.82
    elly
    0.81
    osaurus
    0.80
    Act Density 0.088%

    No Known Activations