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

    Neuronpedia

    INDEX
    Explanations

    adjectives related to high standards or qualities

    oai_token-act-pair · gpt-3.5-turbo

    adjectives describing moral qualities or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     redes
    -0.82
     Hans
    -0.77
     territ
    -0.66
     stripping
    -0.64
     depos
    -0.62
     moons
    -0.61
     mum
    -0.60
     squads
    -0.59
     Reese
    -0.58
     gut
    -0.58
    POSITIVE LOGITS
    able
    2.60
    ably
    2.48
    ability
    2.13
    ables
    2.13
    ABLE
    1.84
    abilities
    1.73
    abl
    1.61
    ible
    1.53
    ibly
    1.53
    abil
    1.51
    Act Density 0.097%

    No Known Activations