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

    Neuronpedia

    INDEX
    Explanations

    phrases that include comparative constructs involving "as."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    achs
    -0.19
    ŀæĢ§
    -0.17
    ittest
    -0.17
    aina
    -0.14
    portion
    -0.14
    ach
    -0.14
    ÑĢоÑĦ
    -0.14
    mans
    -0.14
    rous
    -0.13
    dera
    -0.13
    POSITIVE LOGITS
    ling
    0.17
    .lazy
    0.17
    143
    0.15
    佩
    0.15
    896
    0.14
     simple
    0.14
    Simple
    0.14
     diverse
    0.14
     Victims
    0.14
    γγελ
    0.14
    Act Density 0.028%

    No Known Activations