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

    Neuronpedia

    INDEX
    Explanations

    expressions of indifference or concern in relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aled
    -0.18
    rok
    -0.15
    edia
    -0.15
    dum
    -0.15
    positor
    -0.14
    å¥ı
    -0.14
    ignon
    -0.14
    ulle
    -0.14
    caling
    -0.14
    agn
    -0.14
    POSITIVE LOGITS
     about
    0.22
     cared
    0.22
     cares
    0.20
    lessly
    0.18
     tentang
    0.18
     caring
    0.17
    cter
    0.17
    éĹ²
    0.16
    about
    0.15
    ycl
    0.15
    Act Density 0.018%

    No Known Activations