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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating continuation or inclusion

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

    listing further examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WithIOException
    -0.75
    msgTypes
    -0.71
    principalColumn
    -0.69
    ⎨
    -0.68
    ✨:
    -0.62
    XtraEditors
    -0.60
     myſelf
    -0.59
     Jefus
    -0.59
    Linki
    -0.58
     ||
    -0.58
    POSITIVE LOGITS
    一系列
    0.72
    种种
    0.65
    etera
    0.64
     متعلقه
    0.63
     endless
    0.59
    诸多
    0.59
    ChildIndex
    0.59
     (;;
    0.57
    .
    0.56
     cetera
    0.54
    Act Density 0.039%

    No Known Activations