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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a sense of loss or abandonment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ostel
    -0.15
    rices
    -0.15
    avra
    -0.14
    arin
    -0.14
    lav
    -0.14
    sik
    -0.14
    Stay
    -0.14
    emey
    -0.14
    _MISSING
    -0.14
    reo
    -0.13
    POSITIVE LOGITS
     feeling
    0.23
     wonder
    0.22
     stranded
    0.21
     wondering
    0.21
     with
    0.20
     without
    0.18
     speech
    0.18
     vulnerable
    0.18
     Wonder
    0.17
     Speech
    0.17
    Act Density 0.027%

    No Known Activations