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

    Neuronpedia

    INDEX
    Explanations

    the presence of the name or term "Ab" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ―――――
    -0.85
     Argos
    -0.83
    شهاد
    -0.80
    ).</
    -0.78
     itſelf
    -0.77
     ſche
    -0.77
     Koy
    -0.76
    CreateModel
    -0.75
    ."]
    -0.75
     ་་
    -0.75
    POSITIVE LOGITS
     Ab
    3.35
     ab
    3.07
    Ab
    2.98
    ab
    2.01
     abzu
    1.67
     AB
    1.62
     Аб
    1.50
     ablation
    1.47
     Abby
    1.44
     Abdu
    1.43
    Act Density 0.046%

    No Known Activations