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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the act of surrendering

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "surrender" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    colo
    -0.79
    occ
    -0.77
    updated
    -0.73
    OTH
    -0.73
    OTT
    -0.73
    GROUP
    -0.72
    Adam
    -0.72
    ASS
    -0.70
    ulz
    -0.69
    Compar
    -0.68
    POSITIVE LOGITS
     surrender
    1.28
     surrendered
    1.13
    itures
    0.99
     uncond
    0.98
    itionally
    0.85
    eering
    0.84
    ption
    0.81
    itives
    0.79
     defeat
    0.78
     amnesty
    0.78
    Act Density 0.008%

    No Known Activations