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

    Neuronpedia

    INDEX
    Explanations

    occurrences of ants and their behaviors in a specific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ankan
    -0.16
    rippling
    -0.14
    ripple
    -0.14
    splice
    -0.14
    ulong
    -0.14
    edral
    -0.14
    duck
    -0.14
     breathing
    -0.14
     оÑģÑĮ
    -0.13
    //}}
    -0.13
    POSITIVE LOGITS
     worker
    0.38
     ants
    0.38
     Worker
    0.36
     workers
    0.34
    worker
    0.33
     Workers
    0.33
    Worker
    0.33
     ant
    0.32
     queen
    0.32
    Workers
    0.31
    Act Density 0.024%

    No Known Activations