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

    Neuronpedia

    INDEX
    Explanations

    phrases related to having a purpose or motive

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating roles, responsibilities, or actions related to agency and influence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    EPA
    -0.79
    INC
    -0.78
    MAP
    -0.75
    byss
    -0.74
    NR
    -0.74
    ictionary
    -0.72
    Sport
    -0.72
    aniel
    -0.71
    conn
    -0.70
    NC
    -0.70
    POSITIVE LOGITS
     grasp
    0.72
     appre
    0.72
     hurd
    0.69
     dealing
    0.65
     tow
    0.65
     cameo
    0.64
     knack
    0.64
     vantage
    0.64
     spare
    0.64
     fetish
    0.64
    Act Density 0.279%

    No Known Activations