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

    Neuronpedia

    INDEX
    Explanations

    words related to gravity or attraction

    oai_token-act-pair · gpt-3.5-turbo

    terms related to gravity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ħĭ
    -0.92
     FSA
    -0.69
    ublic
    -0.68
     Lloyd
    -0.67
    LEASE
    -0.67
     Prin
    -0.67
     Reloaded
    -0.66
    OOL
    -0.66
     Continued
    -0.65
    DOS
    -0.65
    POSITIVE LOGITS
     grav
    1.51
    itating
    1.12
    itas
    0.98
    itates
    0.93
    itate
    0.90
    estones
    0.90
    iton
    0.90
    itiz
    0.87
    itated
    0.84
    bent
    0.83
    Act Density 0.005%

    No Known Activations