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

    Neuronpedia

    INDEX
    Explanations

    phrases related to starting or creating something from the beginning

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to starting or building something anew

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Palestin
    -0.75
    ombs
    -0.72
    ossession
    -0.71
    omin
    -0.69
     Ober
    -0.67
    orm
    -0.66
    versely
    -0.65
    relations
    -0.65
     conflic
    -0.63
    inyl
    -0.63
    POSITIVE LOGITS
     scratch
    1.53
     scratched
    1.08
    ratch
    1.07
     scratches
    1.03
    manship
    0.93
     scratching
    0.92
    pad
    0.91
    tenance
    0.90
     slate
    0.89
    lihood
    0.81
    Act Density 0.006%

    No Known Activations