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

    Neuronpedia

    INDEX
    Explanations

    keywords related to server configurations and settings

    oai_token-act-pair · gpt-3.5-turbo

    references to server configurations and security settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     VIDE
    -0.68
     contagious
    -0.61
    ðŁij
    -0.61
     stitch
    -0.60
     hysterical
    -0.60
     briefs
    -0.59
     caut
    -0.57
     kernels
    -0.56
     escorted
    -0.56
     playthrough
    -0.55
    POSITIVE LOGITS
    /-
    0.94
    usterity
    0.85
    etheless
    0.81
    ql
    0.79
    dinand
    0.76
    ploy
    0.75
    manuel
    0.75
    mosp
    0.72
    ility
    0.72
    ¥µ
    0.71
    Act Density 0.112%

    No Known Activations