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

    Neuronpedia

    INDEX
    Explanations

    geographical directions and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    okus
    -0.20
    ephy
    -0.16
    addon
    -0.15
    adder
    -0.15
    ibus
    -0.14
    opr
    -0.14
     vÃŃde
    -0.13
    _GRE
    -0.13
    zech
    -0.13
    adders
    -0.13
    POSITIVE LOGITS
     turn
    0.23
     follow
    0.22
     Turn
    0.21
    gnore
    0.20
     bear
    0.19
     slight
    0.19
    Turn
    0.18
    turn
    0.18
     Follow
    0.18
     bearing
    0.18
    Act Density 0.046%

    No Known Activations