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

    Neuronpedia

    INDEX
    Explanations

    references to likability and shared traits among individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acades
    -0.17
     like
    -0.16
    yme
    -0.15
    ntl
    -0.15
    ocker
    -0.15
    rou
    -0.15
    AGMA
    -0.15
    ÙĬج
    -0.15
    _COMPAT
    -0.15
    виÑĩ
    -0.14
    POSITIVE LOGITS
    -minded
    0.32
     minded
    0.29
     unto
    0.27
    able
    0.23
    WISE
    0.19
    iliki
    0.19
    abled
    0.19
    ewise
    0.18
    uset
    0.18
    /dis
    0.16
    Act Density 0.067%

    No Known Activations