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

    Neuronpedia

    INDEX
    Explanations

    instances of conversational or colloquial expressions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    Hochspringen
    -0.66
    }{*}{
    -0.66
     незавершена
    -0.64
    ölf
    -0.64
    |}{}
    -0.63
    }`}>
    -0.61
    }`}
    -0.60
    ChildScrollView
    -0.59
     HttpNotFound
    -0.59
    ]++;
    -0.58
    POSITIVE LOGITS
     SwitchCompat
    0.68
    意思是
    0.52
    verwijspagina
    0.52
     kasarigan
    0.50
    ียง
    0.50
     ex
    0.49
    Pautan
    0.47
     interlocutor
    0.47
    UnusedPrivate
    0.46
     elicited
    0.45
    Act Density 0.591%

    No Known Activations