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

    Neuronpedia

    INDEX
    Explanations

    mentions of "ters" at the end of a word

    oai_token-act-pair · gpt-3.5-turbo

    words related to "ters," implying a focus on a specific group or category of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     final
    -0.63
     preparation
    -0.62
    Finish
    -0.61
    Fra
    -0.60
     reconstruction
    -0.59
     sudden
    -0.59
    ¢
    -0.59
    ĵ
    -0.58
     subdu
    -0.57
    Shar
    -0.57
    POSITIVE LOGITS
    weet
    1.21
    ters
    1.17
    theless
    1.08
    geist
    1.07
    rane
    0.95
    rors
    0.92
    poons
    0.92
    culosis
    0.92
    witch
    0.91
    rats
    0.89
    Act Density 0.005%

    No Known Activations