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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating stability and support in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æķ·
    -0.16
    rax
    -0.15
    achuset
    -0.15
    eson
    -0.14
    \Migration
    -0.13
    .Toolkit
    -0.13
    073
    -0.13
    pter
    -0.13
    EDI
    -0.13
    ноÑĪ
    -0.13
    POSITIVE LOGITS
     stable
    0.73
     stability
    0.68
    stable
    0.63
     Stable
    0.63
     Stability
    0.61
    稳
    0.59
     stabilize
    0.58
     stabil
    0.58
     steady
    0.56
     stabilization
    0.55
    Act Density 0.393%

    No Known Activations