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

    Neuronpedia

    INDEX
    Explanations

    prominent articles and conjunctions at the beginning of sentences

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

    introducing explanations clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SourceChecksum
    -0.76
    principalColumn
    -0.66
    EDEFAULT
    -0.64
     Verſ
    -0.63
     resourceCulture
    -0.62
     $_(
    -0.60
     myſelf
    -0.59
    protoimpl
    -0.58
     queſta
    -0.58
    ⤹
    -0.58
    POSITIVE LOGITS
    ⇛
    0.34
     autorytatywna
    0.32
     package
    0.31
     bans
    0.31
     arenas
    0.31
    sss
    0.30
    ::
    0.29
    AutoScaleMode
    0.29
    rt
    0.29
    jgl
    0.29
    Act Density 0.073%

    No Known Activations