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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate a basis or foundation for claims, arguments, or assumptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Симпто
    -0.52
    ventory
    -0.47
                                   
    -0.46
     jesús
    -0.44
    getTransaction
    -0.44
     vill
    -0.42
     tqdm
    -0.42
     mcqueen
    -0.42
     Vill
    -0.42
     parliament
    -0.42
    POSITIVE LOGITS
     based
    0.94
     BASED
    0.93
    based
    0.88
     Base
    0.88
     base
    0.86
    BASED
    0.85
    base
    0.83
     Based
    0.82
    Base
    0.81
     Basis
    0.79
    Act Density 0.193%

    No Known Activations