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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate ability and activity in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Provided
    -0.20
     gave
    -0.18
    provided
    -0.16
     provided
    -0.16
     Created
    -0.15
    locator
    -0.15
    è¹
    -0.14
    Provid
    -0.14
    plevel
    -0.14
    Created
    -0.14
    POSITIVE LOGITS
     viewed
    0.39
     seen
    0.36
    seen
    0.35
     heard
    0.33
    Seen
    0.31
     understood
    0.31
     loved
    0.31
     regarded
    0.31
     enjoyed
    0.30
     appreciated
    0.30
    Act Density 0.259%

    No Known Activations