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

    Neuronpedia

    INDEX
    Explanations

    animals and related terms

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to specific roles, relationships, or animals within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    staking
    -0.60
    FUL
    -0.58
     upfront
    -0.56
    iblical
    -0.56
     sooner
    -0.55
    cipled
    -0.55
    ãĤ¨ãĥ«
    -0.55
     awa
    -0.54
     anniversary
    -0.53
    pedia
    -0.52
    POSITIVE LOGITS
    eworks
    0.78
    tones
    0.78
    ress
    0.73
    resses
    0.72
    uits
    0.71
    riks
    0.70
    estyles
    0.68
    blers
    0.67
    ancers
    0.67
    ties
    0.66
    Act Density 0.566%

    No Known Activations