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

    Neuronpedia

    INDEX
    Explanations

    phrases related to leaving and being alone

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kel
    -0.18
    lav
    -0.16
    echa
    -0.15
    GU
    -0.15
    akh
    -0.14
    aÄį
    -0.14
     Missing
    -0.14
     nar
    -0.14
    igy
    -0.14
     Lease
    -0.14
    POSITIVE LOGITS
     alone
    0.42
    alone
    0.35
     Alone
    0.34
    -alone
    0.29
     aside
    0.23
     untouched
    0.23
     intact
    0.22
    à¹Ħว
    0.20
     unchanged
    0.19
    aside
    0.17
    Act Density 0.051%

    No Known Activations