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

    Neuronpedia

    INDEX
    Explanations

    technical terminology related to scientific processes and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .
    -1.15
     
    -1.13
    </s>
    -1.12
     
    -1.11
     ♥
    -1.05
     �
    -1.05
     ‘’
    -1.03
    
    -0.99
    –>
    -0.97
    �
    -0.93
    POSITIVE LOGITS
     $\$
    2.18
     \&
    2.15
     ${
    2.10
    \_
    2.02
     $\
    2.02
     \#
    1.88
     $(\
    1.85
    \&
    1.82
     $=$
    1.80
    \\
    1.75
    Act Density 0.917%

    No Known Activations