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

    Neuronpedia

    INDEX
    Explanations

    information related to species and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Humans
    -0.68
     Owls
    -0.67
    Humans
    -0.63
     humanas
    -0.62
     Swans
    -0.61
     Manusia
    -0.61
     Snakes
    -0.60
     Bees
    -0.60
     Bats
    -0.60
     umane
    -0.59
    POSITIVE LOGITS
     animal
    1.30
     creature
    1.15
    animal
    1.02
     species
    0.96
     crit
    0.92
     organism
    0.89
     animals
    0.84
     beast
    0.80
    creature
    0.76
     creatures
    0.76
    Act Density 0.401%

    No Known Activations