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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of 'looseness' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pleaſure
    -0.88
     Majefty
    -0.88
     Eſ
    -0.84
     Efq
    -0.80
     preſent
    -0.79
     myſelf
    -0.78
     Reſ
    -0.77
     Anſ
    -0.76
     Wię
    -0.76
     Houſe
    -0.75
    POSITIVE LOGITS
     contact
    1.01
     pond
    0.87
    contact
    0.82
     Pond
    0.67
     contacting
    0.67
     Contact
    0.65
     contacts
    0.65
    pond
    0.65
     Roskov
    0.64
     contacter
    0.64
    Act Density 0.168%

    No Known Activations