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

    Neuronpedia

    INDEX
    Explanations

    references to objectives in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ing
    -0.86
    r
    -0.74
     CreateTagHelper
    -0.74
    ness
    -0.72
    ers
    -0.65
    esthes
    -0.64
    ING
    -0.63
     élector
    -0.60
    ings
    -0.57
    uxxxx
    -0.56
    POSITIVE LOGITS
    mente
    0.95
     ―――――
    0.94
     Domes
    0.89
    theless
    0.89
     ――――――――
    0.88
    NUMX
    0.86
     myſelf
    0.84
    marginHorizontal
    0.82
    tely
    0.82
    annica
    0.81
    Act Density 0.237%

    No Known Activations