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

    Neuronpedia

    INDEX
    Explanations

    the presence of specific letters or initials within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anc
    -0.06
    igner
    -0.06
     Din
    -0.05
    PCP
    -0.05
     La
    -0.05
     Jer
    -0.05
    оÑĢдин
    -0.05
    .DEFINE
    -0.05
    pan
    -0.05
    ecs
    -0.05
    POSITIVE LOGITS
    aser
    0.08
    TestingModule
    0.08
    emode
    0.07
     Morrison
    0.07
    ooke
    0.07
    emoc
    0.07
    ased
    0.07
    _dl
    0.07
    unami
    0.07
    aven
    0.07
    Act Density 0.005%

    No Known Activations