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

    Neuronpedia

    INDEX
    Explanations

    phrases related to social media hashtags

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    olivia
    -0.57
    batman
    -0.49
    austin
    -0.46
    joey
    -0.45
    slv
    -0.42
    superman
    -0.42
    harley
    -0.42
    madison
    -0.42
     over
    -0.42
    层面
    -0.41
    POSITIVE LOGITS
    .#
    0.90
     $\#
    0.83
    \#
    0.83
     #
    0.81
     solidar
    0.80
     \#
    0.78
     "#
    0.75
    /#
    0.74
     utop
    0.74
     '#
    0.74
    Act Density 0.066%

    No Known Activations