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

    Neuronpedia

    INDEX
    Explanations

    words related to continuation or ongoing actions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    oster
    -0.89
    ranch
    -0.85
    atana
    -0.84
    ramid
    -0.82
    usterity
    -0.82
    aster
    -0.81
    acus
    -0.79
    onomic
    -0.78
    arta
    -0.76
    dinand
    -0.76
    POSITIVE LOGITS
     unab
    1.00
     uninterrupted
    0.95
     unanswered
    0.85
     ap
    0.85
     indefinitely
    0.85
     unchanged
    0.84
     onward
    0.81
     onwards
    0.80
     progressing
    0.80
    uum
    0.74
    Act Density 9.297%

    No Known Activations