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

    Neuronpedia

    INDEX
    Explanations

    words related to provocative or controversial topics

    oai_token-act-pair · gpt-3.5-turbo

    adverbs that imply an affirmative or positive action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     playbook
    -0.63
    BUS
    -0.60
     machine
    -0.60
     records
    -0.57
     Stanton
    -0.56
     fl
    -0.55
     won
    -0.54
     waves
    -0.54
     Nest
    -0.54
     Machine
    -0.53
    POSITIVE LOGITS
    atively
    4.81
    ative
    2.42
    atives
    2.32
    ially
    1.81
    ativity
    1.79
    ATIVE
    1.60
    ively
    1.41
    ously
    1.39
    ably
    1.39
    ationally
    1.33
    Act Density 0.005%

    No Known Activations