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

    Neuronpedia

    INDEX
    Explanations

    mentions of old objects or individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "old."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utterstock
    -0.87
    ONSORED
    -0.81
    Ĥİ
    -0.81
     athlet
    -0.79
    vous
    -0.77
    ILA
    -0.76
     ILCS
    -0.76
    aminer
    -0.75
    IRO
    -0.74
    amera
    -0.73
    POSITIVE LOGITS
     fashioned
    1.36
    rums
    1.00
    school
    0.93
    est
    0.89
    fashioned
    0.87
     fart
    0.82
     school
    0.79
     standby
    0.78
     timers
    0.73
    boy
    0.73
    Act Density 0.031%

    No Known Activations