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

    Neuronpedia

    INDEX
    Explanations

    words related to surrendering or giving up

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "surrender" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    colo
    -0.77
    çīĪ
    -0.72
    Compar
    -0.69
    Downloadha
    -0.67
    APH
    -0.66
    ova
    -0.64
    INFO
    -0.64
    =#
    -0.63
    GW
    -0.63
     Cosponsors
    -0.61
    POSITIVE LOGITS
     uncond
    1.02
     surrender
    0.83
     peacefully
    0.82
     defeat
    0.79
    ardless
    0.78
     allegiance
    0.77
    selage
    0.76
     surrendered
    0.76
    ylon
    0.74
    itures
    0.72
    Act Density 0.050%

    No Known Activations