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

    Neuronpedia

    INDEX
    Explanations

    references to a specific term, "Boy", often connected to names or groups, with varying levels of relevance indicated by the activation values

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "Boy" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aeda
    -1.16
    aukee
    -0.83
    ickr
    -0.77
     podium
    -0.77
    iment
    -0.72
    encing
    -0.70
    insula
    -0.69
    mble
    -0.68
     instability
    -0.67
    ENC
    -0.66
    POSITIVE LOGITS
    friend
    1.47
    cott
    1.25
     Scouts
    1.20
    hood
    1.16
    boys
    1.15
    boy
    1.12
    nton
    1.08
    friends
    1.07
     Scout
    1.04
    stown
    0.99
    Act Density 0.012%

    No Known Activations