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

    Neuronpedia

    INDEX
    Explanations

    phrases related to characters making physical approaches or movements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     jezelf
    -0.52
     strijd
    -0.43
     zichzelf
    -0.42
     opleiding
    -0.40
     esercit
    -0.39
    anstalt
    -0.38
    Battle
    -0.38
    ComponentScan
    -0.38
     natuurlijke
    -0.37
     dezelve
    -0.37
    POSITIVE LOGITS
     approached
    0.86
     يتيمه
    0.81
    Approach
    0.81
     approaching
    0.77
     Approach
    0.74
     approach
    0.70
     APPROACH
    0.69
     approaches
    0.68
    approach
    0.68
    +#+#
    0.66
    Act Density 0.216%

    No Known Activations