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

    Neuronpedia

    INDEX
    Explanations

    evidence of emotional detachment or a lack of sensitivity in interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilig
    -0.18
    yny
    -0.15
    emin
    -0.14
    elts
    -0.14
    rick
    -0.14
    anship
    -0.13
    atre
    -0.13
    _KP
    -0.13
    AdapterFactory
    -0.13
    irie
    -0.13
    POSITIVE LOGITS
     slightest
    0.20
     anywhere
    0.20
     anything
    0.20
     nÃło
    0.18
     any
    0.18
     anyone
    0.18
     iota
    0.18
     ANY
    0.17
    anything
    0.16
    ENTION
    0.16
    Act Density 0.228%

    No Known Activations