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

    Neuronpedia

    INDEX
    Explanations

    phrases related to leaving objects in certain conditions or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "leaving" or "staying"

    np_acts-logits-general · gemini-2.0-flash

    leaving or remaining in place

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ➯
    -0.66
    ⤹
    -0.64
     للمعارف
    -0.64
    expandindo
    -0.62
     Administrativna
    -0.60
     autorytatywna
    -0.60
    oa̍t
    -0.59
     الرياضيه
    -0.59
    ArgsConstructor
    -0.59
     Wicidata
    -0.57
    POSITIVE LOGITS
     оставля
    0.51
     remain
    0.51
     remained
    0.50
     laiss
    0.49
     left
    0.48
     retained
    0.48
    ไว้
    0.47
     leave
    0.46
     stays
    0.46
     laissé
    0.45
    Act Density 0.512%

    No Known Activations