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

    Neuronpedia

    INDEX
    Explanations

    phrases related to intentions and future actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     مشين
    -0.47
    <?
    -0.47
    میزی
    -0.46
     Thakur
    -0.46
    Climat
    -0.46
     förm
    -0.45
    bld
    -0.45
     osv
    -0.44
    ⎦
    -0.43
     discrimin
    -0.42
    POSITIVE LOGITS
     plans
    1.64
     planned
    1.49
    plans
    1.44
     Plans
    1.39
    Plans
    1.35
    Planned
    1.30
     PLANS
    1.30
     geplant
    1.29
     plan
    1.25
     Planned
    1.24
    Act Density 0.186%

    No Known Activations