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

    Neuronpedia

    INDEX
    Explanations

    phrases related to greetings and common expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ]));
    -0.82
    '){
    -0.74
    '},
    -0.72
     }}$}
    -0.72
    [];
    -0.71
    ")));
    -0.71
    "},
    -0.70
    ('');
    -0.70
    }.
    -0.69
    ]:
    -0.69
    POSITIVE LOGITS
    transQ
    0.56
     @
    0.51
     cor
    0.50
     ma
    0.48
    itatis
    0.48
    ällor
    0.47
    ophi
    0.47
    ,
    0.46
    @
    0.45
    Hola
    0.45
    Act Density 0.089%

    No Known Activations