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

    Neuronpedia

    INDEX
    Explanations

    names of people

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals or names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     apex
    -0.54
     Citiz
    -0.54
     ambassadors
    -0.53
     comprom
    -0.53
     reciprocal
    -0.52
     independents
    -0.51
     rivals
    -0.51
     intermedi
    -0.50
     envy
    -0.49
     psi
    -0.49
    POSITIVE LOGITS
     Jr
    1.00
    owski
    0.95
    chuk
    0.92
    ovich
    0.88
    owicz
    0.86
    iewicz
    0.85
    ansky
    0.85
    baum
    0.84
     (@
    0.84
    berger
    0.83
    Act Density 0.312%

    No Known Activations