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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "Direct" and related terms in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vero
    -0.17
    unter
    -0.17
    rlen
    -0.15
    BSITE
    -0.15
    229
    -0.15
    ä»ĭ
    -0.15
    icals
    -0.15
    omer
    -0.15
    èī²
    -0.15
    flo
    -0.15
    POSITIVE LOGITS
    sdale
    0.16
    thy
    0.15
    tri
    0.15
     Kenny
    0.14
    žel
    0.14
    enské
    0.14
    tol
    0.14
    ummings
    0.14
     otherwise
    0.14
    ="../../../
    0.14
    Act Density 0.017%

    No Known Activations