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

    Neuronpedia

    INDEX
    Explanations

    references to geographic features, specifically lakes and campuses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     directly
    -0.47
     available
    -0.42
    ,
    -0.42
     also
    -0.41
     set
    -0.41
     lower
    -0.40
     associated
    -0.40
     definitely
    -0.40
     either
    -0.40
     mis
    -0.39
    POSITIVE LOGITS
    VYMaps
    0.93
    <unused43>
    0.91
    <unused41>
    0.90
    <unused74>
    0.90
    <unused42>
    0.90
    <pad>
    0.90
    <unused28>
    0.90
    <unused51>
    0.90
    <unused8>
    0.90
    <unused3>
    0.90
    Act Density 0.281%

    No Known Activations