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

    Neuronpedia

    INDEX
    Explanations

    verbs related to creating or executing actions

    oai_token-act-pair · gpt-3.5-turbo

    references to actions and their consequences, particularly in relation to accountability and government or organizational structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utm
    -0.74
     Niet
    -0.73
    è¦
    -0.73
    cair
    -0.67
    verages
    -0.67
    Avg
    -0.62
    staking
    -0.62
     Juda
    -0.62
    ãĤ¸
    -0.60
    igor
    -0.59
    POSITIVE LOGITS
     disappear
    1.22
     happen
    1.20
     vanish
    1.07
     available
    1.05
     accessible
    1.05
     unavailable
    0.96
     appear
    0.95
     look
    0.88
     explode
    0.87
     compulsory
    0.87
    Act Density 0.187%

    No Known Activations