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

    Neuronpedia

    INDEX
    Explanations

    and highlight names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals associated with comments or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tumblr
    -0.85
     derailed
    -0.78
     resulted
    -0.72
     proves
    -0.72
     interfered
    -0.72
     proved
    -0.72
     matured
    -0.72
     discriminated
    -0.70
     existed
    -0.69
     collided
    -0.68
    POSITIVE LOGITS
    anton
    0.81
    leigh
    0.79
    emon
    0.77
     Cohen
    0.75
    imir
    0.75
     Shapiro
    0.72
     Lindsey
    0.72
     Rank
    0.72
     Brow
    0.70
    uria
    0.70
    Act Density 0.142%

    No Known Activations