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

    Neuronpedia

    INDEX
    Explanations

    terms related to the process of transition or transformation

    oai_token-act-pair · gpt-3.5-turbo

    terms related to transition and transformation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     vengeance
    -0.74
     Ivy
    -0.73
     Lawn
    -0.72
     Avery
    -0.70
     finger
    -0.69
     Brist
    -0.69
     Fury
    -0.67
     stomp
    -0.65
     matchup
    -0.64
     swear
    -0.64
    POSITIVE LOGITS
    trans
    4.04
    Trans
    2.53
    translation
    2.02
     Trans
    1.95
    rans
    1.88
     TRANS
    1.81
     trans
    1.65
     TRAN
    1.51
    transform
    1.49
    transfer
    1.36
    Act Density 0.012%

    No Known Activations