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

    Neuronpedia

    INDEX
    Explanations

    phrases related to leaving or departing from a place or situation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "leave" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alist
    -0.95
    intend
    -0.74
    ians
    -0.73
    andan
    -0.70
    lied
    -0.69
    hemy
    -0.67
    attribute
    -0.65
    inarily
    -0.65
    ensity
    -0.65
    ethical
    -0.65
    POSITIVE LOGITS
     undone
    1.06
     behind
    1.03
     town
    1.00
     footprints
    0.92
    overs
    0.82
     unfinished
    0.82
     aside
    0.80
     voluntarily
    0.79
     academia
    0.79
     voic
    0.78
    Act Density 0.052%

    No Known Activations