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

    Neuronpedia

    INDEX
    Explanations

    words related to computer technology and software

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to web-based technology and cyber activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ital
    -0.82
     halftime
    -0.77
     Klu
    -0.76
     Lowry
    -0.73
     disband
    -0.72
     regard
    -0.72
     subsequ
    -0.71
     Kenny
    -0.71
     proclamation
    -0.69
     Kirk
    -0.69
    POSITIVE LOGITS
    enabled
    1.62
    based
    1.54
    driven
    1.51
    friendly
    1.48
    sav
    1.44
    generated
    1.44
    mediated
    1.41
    intensive
    1.40
    assisted
    1.39
    centric
    1.37
    Act Density 0.061%

    No Known Activations