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

    Neuronpedia

    INDEX
    Explanations

    references to personal relationships and feelings of connection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    keep you/me/us/him

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ThroughAttribute
    -0.52
    esModule
    -0.49
    gleiche
    -0.48
     intptr
    -0.47
    scalatest
    -0.47
     OnInit
    -0.47
     BitmapFactory
    -0.47
    NoSuchAlgorithm
    -0.46
    ihnachts
    -0.46
    ༘
    -0.46
    POSITIVE LOGITS
     Keep
    0.82
     keep
    0.82
     kept
    0.81
    Keep
    0.80
     Keeps
    0.77
    keep
    0.75
     keeps
    0.75
    Keeps
    0.73
     Kept
    0.73
    Stay
    0.72
    Act Density 0.009%

    No Known Activations