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

    Neuronpedia

    INDEX
    Explanations

    geographical directions in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -0.99
     itſelf
    -0.86
     AssemblyTitle
    -0.82
     referenties
    -0.82
     myſelf
    -0.81
     Monfieur
    -0.75
     ſche
    -0.69
     faſt
    -0.69
     iſt
    -0.69
    ModelSerializer
    -0.69
    POSITIVE LOGITS
    rinfo
    0.67
     north
    0.65
     south
    0.64
    ConstraintMaker
    0.63
     past
    0.59
     east
    0.57
     виправивши
    0.56
    locaust
    0.56
    ecore
    0.54
     west
    0.54
    Act Density 0.131%

    No Known Activations