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

    Neuronpedia

    INDEX
    Explanations

    hierarchical structures or concepts involving subscripts and superscripts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     transfieras
    -0.67
    endpush
    -0.63
    ()])
    -0.60
    <?=$
    -0.59
    vax
    -0.59
     &___
    -0.58
    AnchorTagHelper
    -0.58
    ()?;
    -0.55
    <?=
    -0.55
    !("{}",
    -0.54
    POSITIVE LOGITS
    mrow
    0.59
     الرياضيه
    0.52
     mattina
    0.47
    redients
    0.46
    iliz
    0.46
     filial
    0.46
     almoço
    0.46
    UserScript
    0.44
    urator
    0.44
     damas
    0.43
    Act Density 0.235%

    No Known Activations