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

    Neuronpedia

    INDEX
    Explanations

    phrases related to image resolution

    oai_token-act-pair · gpt-3.5-turbo

    terms related to solutions and resolutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     watches
    -0.67
     Carib
    -0.66
     bree
    -0.64
     critically
    -0.62
     watch
    -0.61
     possibly
    -0.60
     fumes
    -0.60
     PJ
    -0.60
     alert
    -0.59
     stud
    -0.59
    POSITIVE LOGITS
    olution
    4.53
    olutions
    2.65
    olved
    2.44
    olving
    2.18
    olve
    2.14
    olves
    2.00
    olver
    1.65
    Solution
    1.57
     Solution
    1.27
    urrection
    1.24
    Act Density 0.010%

    No Known Activations