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

    Neuronpedia

    INDEX
    Explanations

    phrases related to leaving a place or situation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "leave."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    reme
    -0.81
    alist
    -0.75
    insula
    -0.73
    gio
    -0.69
    MpServer
    -0.68
    andan
    -0.65
    inarily
    -0.65
    intend
    -0.64
    yrinth
    -0.63
    kered
    -0.62
    POSITIVE LOGITS
     undone
    0.98
    overs
    0.90
    ipp
    0.77
    wich
    0.74
     Leaves
    0.73
     Aleppo
    0.72
     untreated
    0.71
     unexpl
    0.69
     overboard
    0.68
    ings
    0.66
    Act Density 0.041%

    No Known Activations