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

    Neuronpedia

    INDEX
    Explanations

    verbs related to discovery, realization, or decision-making

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of discovery and situational transitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ©¶æ¥µ
    -0.82
     respectively
    -0.74
     They
    -0.68
    they
    -0.68
    ©¶æ
    -0.64
    cour
    -0.63
     they
    -0.62
    numbered
    -0.59
    iscons
    -0.59
    arming
    -0.59
    POSITIVE LOGITS
     itself
    1.77
     its
    1.46
     ITS
    1.32
    Its
    1.31
     Its
    1.28
     decay
    0.74
    inventoryQuantity
    0.74
     me
    0.73
     us
    0.71
     relevance
    0.70
    Act Density 0.606%

    No Known Activations