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

    Neuronpedia

    INDEX
    Explanations

    phrases that include "based on" to indicate sources or foundations for arguments or perspectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SCALL
    -0.15
    rella
    -0.15
    ìĪ
    -0.14
    conto
    -0.14
    à¸Ħาส
    -0.14
    λλ
    -0.14
    ifth
    -0.14
    rical
    -0.14
    _MAPPING
    -0.14
    OCUMENT
    -0.13
    POSITIVE LOGITS
    ymous
    0.16
    shore
    0.15
    entric
    0.15
    _interfaces
    0.14
     principles
    0.14
     principle
    0.14
    rado
    0.13
    patch
    0.13
    frag
    0.13
    frei
    0.13
    Act Density 0.064%

    No Known Activations