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

    Neuronpedia

    INDEX
    Explanations

    statements related to educational development and overcoming challenges through supportive strategies

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

    following "to"

    np_acts-logits-general · gemini-2.0-flash

    purpose or result

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    \
    -0.53
    ,
    -0.51
    -
    -0.50
     \
    -0.49
     because
    -0.48
    g
    -0.48
    d
    -0.48
    in
    -0.47
     
    -0.47
    x
    -0.46
    POSITIVE LOGITS
     itſelf
    1.25
     myſelf
    1.16
     themſelves
    1.09
    ſelves
    1.03
     Monfieur
    1.00
     poffible
    0.98
    ſelf
    0.95
     uſed
    0.94
     againſt
    0.93
     preſent
    0.93
    Act Density 0.353%

    No Known Activations