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

    Neuronpedia

    INDEX
    Explanations

    parts of text that discuss privacy and surveillance concerns

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    oneofs
    -0.54
    ↵
    -0.50
     maî
    -0.50
    Poloha
    -0.49
    oredCriteria
    -0.47
     typelib
    -0.47
    ↵↵
    -0.46
    Werdegang
    -0.44
    IImage
    -0.43
    <strong>
    -0.41
    POSITIVE LOGITS
    RenderAtEndOf
    0.91
    躇
    0.77
    OOTDTY
    0.74
     мәкал
    0.69
     kasarigan
    0.68
    stdc
    0.66
    醐
    0.66
    󠁣
    0.65
    pidou
    0.64
    Bissau
    0.63
    Act Density 0.010%

    No Known Activations