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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing necessity or importance in a context

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

    be a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ſelf
    -0.66
     Majefty
    -0.60
     Houſe
    -0.60
     Monfieur
    -0.57
     ſta
    -0.57
     purpoſe
    -0.56
     houſe
    -0.55
     tartalomajánló
    -0.55
    EndContext
    -0.53
    NameInMap
    -0.53
    POSITIVE LOGITS
     very
    0.47
     also
    0.42
     not
    0.41
     H
    0.41
    .
    0.40
     always
    0.40
     I
    0.40
     =
    0.40
     L
    0.39
     only
    0.39
    Act Density 0.270%

    No Known Activations