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

    Neuronpedia

    INDEX
    Explanations

    mentions of financial transactions or predictions

    oai_token-act-pair · gpt-3.5-turbo

    themes related to destruction and its consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     respectively
    -0.78
     THEY
    -0.68
    they
    -0.68
     They
    -0.62
    They
    -0.62
    wagen
    -0.61
    MpServer
    -0.61
    éĩ
    -0.61
    sbm
    -0.58
    çĶ°
    -0.57
    POSITIVE LOGITS
     its
    2.26
     Its
    1.96
    Its
    1.82
     itself
    1.53
     ITS
    1.51
    its
    1.17
     it
    0.63
    eatures
    0.62
    stood
    0.58
    pires
    0.56
    Act Density 2.059%

    No Known Activations