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

    Neuronpedia

    INDEX
    Explanations

    references to causality and causal relationships

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

    "ca" followed by a letter

    np_acts-logits-general · gemini-2.0-flash

    causal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Geplaatst
    -0.94
     للمعارف
    -0.87
     Савезне
    -0.75
    ScopeManager
    -0.72
    #+#
    -0.71
    براير
    -0.69
    posedge
    -0.69
    anmoins
    -0.69
    .*")]
    -0.69
    öffnet
    -0.68
    POSITIVE LOGITS
     Ca
    0.58
     ca
    0.54
    Ca
    0.51
    Captor
    0.48
    usual
    0.46
    react
    0.45
    oose
    0.44
    ca
    0.40
     Cahill
    0.40
    dr
    0.38
    Act Density 0.125%

    No Known Activations