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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     rig
    -0.15
     Rig
    -0.15
     resume
    -0.15
    rig
    -0.15
    olean
    -0.14
     اخ
    -0.14
    izens
    -0.14
    нила
    -0.14
     ret
    -0.14
     vice
    -0.14
    POSITIVE LOGITS
     power
    0.27
     raised
    0.26
    power
    0.24
    -power
    0.24
    raised
    0.24
     Raised
    0.24
    .power
    0.22
    POWER
    0.21
     powers
    0.21
     POWER
    0.21
    Act Density 0.150%

    No Known Activations