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

    Neuronpedia

    INDEX
    Explanations

    mentions of the word 'inter' at different parts of the document

    oai_token-act-pair · gpt-3.5-turbo

    instances of the substring "inter" across various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bottled
    -0.66
     owed
    -0.66
     Norn
    -0.64
     spelled
    -0.64
     slate
    -0.64
     guaranteed
    -0.63
     buds
    -0.63
     HG
    -0.62
     cand
    -0.62
     helium
    -0.62
    POSITIVE LOGITS
    inter
    4.25
    inters
    2.69
    INTER
    2.22
    Inter
    2.05
     Inter
    1.50
    agg
    1.35
     INTER
    1.31
    int
    1.27
    INT
    1.25
     inter
    1.16
    Act Density 0.012%

    No Known Activations