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

    Neuronpedia

    INDEX
    Explanations

    different forms of the verb "say" and related expressions of communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mities
    -0.55
    ēj
    -0.52
     Référence
    -0.52
    ways
    -0.51
    SequentialGroup
    -0.51
    Poloha
    -0.50
    tagHelperRunner
    -0.49
     angegeben
    -0.48
    WAYS
    -0.47
    kenstock
    -0.47
    POSITIVE LOGITS
     goodbye
    1.47
     hello
    1.14
    goodbye
    0.95
     thank
    0.92
     yes
    0.91
     farewell
    0.88
     adiós
    0.86
     bye
    0.85
     something
    0.82
     Goodbye
    0.80
    Act Density 0.120%

    No Known Activations