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

    Neuronpedia

    INDEX
    Explanations

    words related to betrayal or wrongdoing

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "traverse" or related concepts of crossing or moving through

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãģ®éŃĶ
    -0.67
    hyde
    -0.67
     retention
    -0.63
     Mellon
    -0.61
    eer
    -0.61
    enture
    -0.61
     CTR
    -0.60
     Safe
    -0.59
    oak
    -0.58
    ATES
    -0.58
    POSITIVE LOGITS
    ppings
    1.34
    vest
    1.31
    pez
    1.24
    itors
    1.06
    vert
    1.01
    ips
    0.97
    wl
    0.96
    izoph
    0.90
    ppers
    0.88
    ordinary
    0.87
    Act Density 0.016%

    No Known Activations