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

    Neuronpedia

    INDEX
    Explanations

    terms related to anchoring and anchors in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enums
    -0.16
    826
    -0.15
    tpl
    -0.15
    ular
    -0.15
    اÙĨÙĩ
    -0.15
    ÙĬØ©
    -0.14
    UDA
    -0.14
    iyah
    -0.14
    eer
    -0.14
    ullan
    -0.14
    POSITIVE LOGITS
     anchor
    0.23
    orage
    0.23
     anchors
    0.19
    (anchor
    0.18
    ovies
    0.18
    less
    0.18
    woman
    0.17
    anchor
    0.17
    oring
    0.17
    anchors
    0.17
    Act Density 0.007%

    No Known Activations