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

    Neuronpedia

    INDEX
    Explanations

    negative descriptors and references to damage or problematic situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RIPT
    -0.17
    aney
    -0.16
    kud
    -0.15
    ugi
    -0.14
    ipa
    -0.14
    iang
    -0.14
    oret
    -0.13
    aneous
    -0.13
    ernels
    -0.13
    ildren
    -0.13
    POSITIVE LOGITS
     Tir
    0.17
     Mos
    0.15
    ,
    0.15
    joint
    0.14
    .activ
    0.14
    aes
    0.13
     cler
    0.13
    oling
    0.13
     op
    0.13
    oki
    0.13
    Act Density 0.000%

    No Known Activations