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

    Neuronpedia

    INDEX
    Explanations

    phrases related to being out of control or out of touch with something specific

    oai_token-act-pair · gpt-3.5-turbo

    terms related to being "out of touch" or "out of control"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nai
    -0.80
    ãĤ¶
    -0.80
    ioxide
    -0.79
    advertisement
    -0.74
    ucc
    -0.74
    ellow
    -0.70
    wick
    -0.70
    eely
    -0.70
    arnaev
    -0.69
    incial
    -0.69
    POSITIVE LOGITS
     altogether
    0.86
     entirely
    0.76
     distractions
    0.69
     situations
    0.68
     academ
    0.62
     completely
    0.62
     syndrome
    0.61
     catast
    0.60
     circumstances
    0.60
     curfew
    0.59
    Act Density 0.108%

    No Known Activations