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

    Neuronpedia

    INDEX
    Explanations

    references to penguins

    oai_token-act-pair · gpt-3.5-turbo

    mentions of penguins

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Interstitial
    -0.94
    PART
    -0.72
    earchers
    -0.72
    nerg
    -0.71
    ¿½
    -0.71
    ALLY
    -0.69
    MED
    -0.69
    nda
    -0.68
    WORK
    -0.68
    SOURCE
    -0.67
    POSITIVE LOGITS
     pengu
    1.12
     Penguins
    0.94
    insula
    0.90
     Penguin
    0.87
    oleon
    0.78
     Pengu
    0.78
    emonium
    0.75
     Hots
    0.74
    atoon
    0.74
     Luigi
    0.72
    Act Density 0.010%

    No Known Activations