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

    Neuronpedia

    INDEX
    Explanations

    references to criminal activity, particularly burglary and theft

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     viol
    -0.16
    nett
    -0.15
    itas
    -0.14
    .INPUT
    -0.14
    ots
    -0.14
    OTS
    -0.14
     Lump
    -0.13
    QU
    -0.13
     tie
    -0.13
    .pag
    -0.13
    POSITIVE LOGITS
     stored
    0.18
    eric
    0.18
     Stored
    0.17
    ambi
    0.17
     stealing
    0.17
    linger
    0.16
    cht
    0.16
     stole
    0.16
     stolen
    0.16
    unda
    0.16
    Act Density 0.151%

    No Known Activations