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

    Neuronpedia

    INDEX
    Explanations

    connections and relationships expressed through conjunctions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atcher
    -0.17
    Aware
    -0.15
    æĻ
    -0.14
    ITY
    -0.14
    èİ
    -0.13
    bard
    -0.13
    STALL
    -0.13
    boy
    -0.13
    aware
    -0.12
    .Abstractions
    -0.12
    POSITIVE LOGITS
     others
    0.24
     countless
    0.18
     myself
    0.17
    ">//
    0.16
    çĶļèĩ³
    0.15
    jal
    0.15
     even
    0.15
    ska
    0.15
     Others
    0.14
     surtout
    0.14
    Act Density 0.116%

    No Known Activations