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

    Neuronpedia

    INDEX
    Explanations

    concepts related to scavenging and the physical attributes of species

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     half
    -0.16
    quine
    -0.16
    762
    -0.15
    jar
    -0.15
    agar
    -0.14
    èĽ
    -0.14
     Half
    -0.14
    half
    -0.14
    rieve
    -0.14
    dra
    -0.14
    POSITIVE LOGITS
     adaptations
    0.19
    adapt
    0.18
     specialization
    0.17
     specialised
    0.17
     adaptation
    0.17
     specialized
    0.16
     unarmed
    0.15
     Adapt
    0.15
     evolved
    0.15
     sucker
    0.14
    Act Density 0.063%

    No Known Activations