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

    Neuronpedia

    INDEX
    Explanations

    phrases related to states or actions that are ongoing or in progress

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to resilience and survival

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    encers
    -0.64
    ©¶æ¥µ
    -0.62
    GROUP
    -0.57
    venth
    -0.55
     encouraged
    -0.55
     respectively
    -0.54
    allas
    -0.53
    avid
    -0.53
    rone
    -0.52
    items
    -0.51
    POSITIVE LOGITS
     its
    0.82
     itself
    0.80
     ITS
    0.77
    inventoryQuantity
    0.74
     decay
    0.68
    Its
    0.65
     Its
    0.64
     decom
    0.63
     belonged
    0.62
     hiber
    0.62
    Act Density 1.296%

    No Known Activations